This directory is created automatically and some papers may be mislabeled. Only document within the CiteSeer database are listed. The directory is intended to provide entry points for browsing the database and is not intended to be authoritative. Papers may not appear in all relevant categories. For example, papers in a sub-category may not appear in higher level categories.
539 Finding Structure in Time - Elman (1990)(Correct)
Time underlies many interesting human behaviors. Thus, the question of how to represent time in connectionist models is very important. One approach is to represent time implicitly by its effects on p... / tree but the research in natural language parsing suggests that the br problems that are relevant to natural language processing. The approach
338 KQML as an Agent Communication Language - Finin, Fritzson, McKay, McEntire (1994)(Correct)
This paper describes the design of and experimentation with
the Knowledge Query and Manipulation Language (KQML),
a new language and protocol for exchanging information
and knowledge. This work is par... / as event simulation applied natural language processing knowledge-based
193 A Simple Rule-Based Part Of Speech Tagger - Brill (1992)(Correct)
Automatic part of speech tagging is an area of natural language
processing where statistical techniques have been more
successful than rule-based methods. In this paper, we present
a simple rule-based... / speech tagging is an area of natural language processing where statistical br of probabilistic models to natural language processing over the last few
183 The Oz Programming Model - Smolka (1995)(Correct)
The Oz Programming Model (OPM) is a concurrent programming model subsuming higher- order functional and object-oriented programming as facets of a general model. This is particularly interesting for c... / multi-agent systems natural language processing virtual reality
179 Logic Programming in a Fragment of Intuitionistic Linear Logic - Hodas, Miller (1994)(Correct)
When logic programming is based on the proof theory of intuitionistic logic, it is natural
to allow implications in goals and in the bodies of clauses. Attempting to prove a goal of
the form D oe G fr... / taken from theorem proving natural language parsing and data base br eigen-variables of a proof in natural language parsers they can be used to
167 Letizia: An Agent That Assists Web Browsing - Lieberman (1995)(Correct)
Letizia is a user interface agent that assists a
user browsing the World Wide Web. As the
user operates a conventional Web browser such
as Netscape, the agent tracks user behavior and
attempts to anti... / Letizia does not have natural language understanding capability so br a list of keywords. Partial natural language capabilities that can
163 Recursive Distributed Representations - Pollack (1990)(Correct)
A long-standing difficulty for connectionist modeling has been how to represent
variable-sized recursive data structures, such as trees and lists, in fixed-width patterns.
This paper presents a connec... / cognitive tasks such as Natural Language Processing has been the br this paper by noting that natural language processing posed some
133 A Softbot-Based Interface to the Internet - Etzioni, Weld (1994)(Correct)
this article, we focus on the ideas underlying the softbot-based interface. unknown A Softbot-Based Interface to the Internet
Oren Etzioni
Daniel Weld
Department of Computer Science and Engineering... / any dialog modality e.g.natural language speech and pen interfaces br circumvents the problem of natural-language understanding the agent
129 A Practical Part-of-Speech Tagger - Doug Cutting (1992)(Correct)
We present an implementation of a part-of-speech
tagger based on a hidden Markov model. The
methodology enables robust and accurate tagging
with few resource requirements. Only a lexicon
and some unla... / Second Conference on Applied Natural Language Processing ACL pages br M. Derouault and B. Merialdo. Natural language modeling for phonemeto text
128 A Scalable Comparison-Shopping Agent for the World-Wide Web - Doorenbos, Etzioni, Weld (1997)(Correct)
The Web is less agent-friendly than we might hope. Most information on the Web is presented
in loosely structured natural language text with no agent-readable semantics. HTML annotations
structure the... / in loosely structured natural language text with no agent-readable br without sophisticated natural language processing and requires
123 Transformation-Based Error-Driven Learning and Natural Language.. - Brill (1995)(Correct)
this paper, we will describe a simple rule-based approach to automated learning of linguistic knowledge. This approach has been shown for a number of tasks to capture information in a clearer and more... / Error-Driven Learning and Natural Language Processing A Case Study in br of empiricism in the field of natural language processing. Manual encoding
120 WebWatcher: A Tour Guide for the World Wide Web - Joachims, Freitag, Mitchell (1997)(Correct)
We explore the notion of a tour guide software agent for assisting users browsing the World Wide Web. A Web tour guide agent provides assistance similar to that provided by a human tour guide in a mus... / systems that carry on general natural language dialogs with their users
113 A Maximum Entropy Approach to Natural Language Processing - Berger, Pietra, Pietra (1996)(Correct)
The concept of maximum entropy can be traced back along multiple threads to Biblical times. Only recently, however, have computers become powerful enough to permit the widescale application of this co... / A Maximum Entropy Approach to Natural Language Processing Adam L. Berger br examples several problems in natural language processing. .
106 A Really Temporal Logic - Alur, Henzinger (1989)(Correct)
We introduce a temporal logic for the specification of real-time systems.
Our logic, TPTL, employs a novel quantifier construct for referencing time: the freeze
quantifier binds a variable to the ti... / context. TPTL is both a natural language for specification and a
99 On The Acceptability Of Arguments And Its Fundamental Role In.. - Dung (1995)(Correct)
The purpose of this paper is to study the fundamental mechanism, humans use in argumentation, and to explore ways to implement this mechanism on computers. We do so by first developing a theory for ar... / semantics of logic and natural language The understanding
99 Accurate Methods for the Statistics of Surprise and Coincidence - Dunning (1993)(Correct)
Much work has been done on the statistical analysis of text. In some cases reported in the literature, inappropriate statistical methods have been used, and statistical significance of results have no... / in information retrieval and natural language processing in general.
98 Distributional Clustering of English Words - Pereira, Tishby, Lee (1993)(Correct)
We describe and experimentally evaluate a method for automatically clustering words according to their distribution in particular syntactic contexts. Deterministic annealing is used to find lowest dis... / modeling techniques for natural language rely instead on hard br Class-based n-gram models of natural language. In Proceedings of the IBM
96 Investigations Into a Theory of Knowledge Base Revision - Dalal (1988)(Correct)
A fundamental problem in knowledge representation is how to revise knowledge when new, contradictory information is obtained. This paper formulates some desirable principles of knowledge revision, and... / updates planning and natural language understanding. In this
86 A Scheme for Integrating Concrete Domains into Concept Languages - Baader, Hanschke (1991)(Correct)
A drawback which concept languages based on kl-one have is that all the terminological
knowledge has to be defined on an abstract logical level. In many applications,
one would like to be able to refe... / developed for the purpose of natural language processing Brachman et br drawback already appears in natural language processing it becomes even
71 Inference Networks for Document Retrieval - Turtle (1991)(Correct)
Information retrieval is concerned with selecting documents from a collection that will be of interest to a user with a stated information need or query. Research aimed at improving the performance of... / of CR categories added to natural language query . br query is often expressed in natural language but other forms are possible
69 A Comparison of Two Learning Algorithms for Text Categorization - Lewis, Ringuette (1994)(Correct)
This paper examines the use of inductive learning to categorize natural language documents into predefined content categories. Categorization of text is of increasing importance in information retriev... / learning to categorize natural language documents into predefined br in information retrieval and natural language processing systems. Previous
67 Communicative Actions for Artificial Agents - Cohen, Levesque (1995)(Correct)
This paper considers the semantics of the agent communication
language KQML. By using this language
for communication, agents will be able to request
and provide services. Indeed, numerous projects ha... / Performatives In natural languages a performative utterance is br problem of performatives for natural language speech act theories then
66 Inducing Features of Random Fields - Pietra, Pietra, Lafferty (1997)(Correct)
We present a technique for constructing random fields from a
set of training samples. The learning paradigm builds increasingly complex
fields by allowing potential functions, or features, that are su... / word classification in natural language processing. Keywords- br clustering word morphology natural language processing. I.
64 Partial Parsing via Finite-State Cascades - Abney (1996)(Correct)
Finite-state cascades represent an attractive architecture for parsing
unrestricted text. Deterministic parsers specified by finite-state cascades
are fast and reliable. They can be extended at modest... / applied finite transducers to natural-language Steven Abney
63 Selection And Information: A Class-based Approach to Lexical.. - Resnik (1993)(Correct)
Selectional constraints are limitations on the applicability of predicates to arguments. For example, the statement "The number two is blue" may be syntactically well formed, but at some level it is a... / also as tools for practical natural language processing. v br the IRCS postdocs and the natural language faculty at Penn -for
61 Automatically Constructing a Dictionary for Information Extraction.. - Riloff (1993)(Correct)
Knowledge-based natural language processing systems have
achieved good success with certain tasks but they are often
criticized because they depend on a domain-specific
dictionary that requires a grea... / Abstract Knowledge-based natural language processing systems have br Knowledge-based natural language processing NLP systems
60 Class-based n-gram models of natural language - Brown, Pietra, deSouza, Lai, Mercer (1990)(Correct)
We address the problem of predicting a word from previous words in a sample of text.
In particular, we discuss n-gram models based on classes of words. We also discuss several
statistical algorithms f... / Class-based n-gram models of natural language Peter F. Brown Vincent J. br Introduction In a number of natural language processing tasks we face the
60 A Theoretical Evaluation of Selected Backtracking Algorithms - Kondrak (1994)(Correct)
In recent years, numerous new backtracking algorithms have been proposed. The algorithms are usually evaluated by empirical testing. This method, however, has its limitations. Our thesis adopts a diff... / coloring scene labelling natural language parsing and temporal
60 A semantics approach for KQML - a general purpose communication.. - Labrou, Finin (1994)(Correct)
We investigate the semantics for Knowledge Query Manipulation
Language (KQML) and we propose a semantic framework
for the language. KQML is a language and a protocol
to support communication between s... / description is based on natural language descriptions of its br six constituents . A natural language description of the
56 Computational Complexity of Terminological Reasoning in BACK - Nebel (1988)(Correct)
Terminological reasoning is a mode of reasoning all hybrid knowledge
representation systems based on KL-ONE rely on. After a short introduction
of what terminological reasoning amounts to, it is prove... / reasoner is employed in a natural language generation system cf. the br alternative for example in natural language generation because
56 Temporal Query Languages: a Survey - Chomicki (1995)(Correct)
We define formal notions of temporal domain and temporal database, and use them
to survey a wide spectrum of temporal query languages. We distinguish between an
abstract temporal database and its conc... / paper. For now the following natural language example should help to
54 Active Learning with Statistical Models - Cohn, Ghahramani, Jordan (1996)(Correct)
For many types of machine learning algorithms, one can compute the statistically "optimal
" way to select training data. In this paper, we review how optimal data selection
techniques have been used w... / classify an unknown word in a natural language understanding problem. When
54 Ontology-based Web Agents - Luke, Spector, Rager, Hendler (1997)(Correct)
This paper describes SHOE, a set of Simple HTML Ontology Extensions which allow World-Wide Web authors to annotate their pages with semantic knowledge such as "I am a graduate student" or "This person... / even with state-of-the-art natural language processing techniques index br tags. The current state of natural language processing technology makes
53 Dynamic Montague Grammar - Groenendijk, Stokhof (1989)(Correct)
this paper is based was presented on several occasions, the first of which
was the Stuttgart conference on discourse representation theory, held in November 1987. Various
people have given us the bene... / model-theoretic semantics for natural language are over. And rightly so br the most central principles in natural language semantics see Groenendijk
53 Semantics for an Agent Communication Language - Labrou, Finin (1996)(Correct)
We address the issue of semantics for an agent communication language.
In particular, the semantics of Knowledge Query Manipulation Language
(KQML) is investigated. KQML is a language and protocol t... / of the performatives A natural language description of the br as a formalization of the natural language description
48 Has a Consensus NL Generation Architecture Appeared, and is it.. - Reiter (1994)(Correct)
I survey some recent applications-oriented
NL generation systems, and claim that despite
very different theoretical backgrounds,
these systems have a remarkably similar architecture
in terms of the mo... / PENMAN Penman Natural Language Group Under br In G. Kempen editor Natural Language Generation New Directions
48 Learning to Extract Text-based Information from the World Wide Web - Soderland (1997)(Correct)
There is a wealth of information to be mined from narrative text on the World Wide Web. Unfortunately, standard natural language processing (NLP) extraction techniques expect full, grammatical sentenc... / Web. Unfortunately standard natural language processing NLP extraction br progress has been made in natural language processing text extraction
48 The Design of Nectar: A Network Backplane for Heterogeneous.. - Arnould (1989)(Correct)
Nectar is a "network backplane" for use in heterogeneous
multicomputers. The initial system consists of a starshaped
fiber-optic network with an aggregate bandwidth
of 1.6 gigabits/second and a switch... / processing and high-level natural language parsing. The processing
48 Vision Texture for Annotation - Picard, Minka (1995)(Correct)
This paper demonstrates a new application of
computer vision to digital libraries -- the use of
texture for annotation, the description of content.
Vision-based annotation assists the user
in attachin... / computer programs based on natural language processing and artificial
47 Predicate Logic Unplugged - Bos (1995)(Correct)
this paper we describe the syntax and semantics of a description language for
underspecified semantic representations. This concept is discussed in general and in
particular applied to Predicate Logic... / semantic representations for natural language expressions emerges directly br directly from practical natural language processing applications. The
47 Subtopic Structuring for Full-Length Document Access - Hearst (1993)(Correct)
We argue that the advent of large volumes of full-length text, as opposed to short texts
like abstracts and newswire, should be accompanied by corresponding new approaches to
information access. Towar... / of an abstract when using a natural-language based IR approach These
45 Finite-State Transducers in Language and Speech Processing - Mohri (1997)(Correct)
Finite-state machines have been used in various domains of natural language processing. We consider here the use of a type of transducers that supports very efficient programs: sequential transducers.... / used in various domains of natural language processing. We consider here br Their recent applications in natural language processing which range from
43 Relational Learning of Pattern-Match Rules for Information Extraction - Califf, Mooney (1997)(Correct)
Information extraction is a form of shallow text
processing that locates a specified set of relevant
items in a natural-language document. Systems
for this task require significant domain-specific
kno... / set of relevant items in a natural-language document. Systems for this br on the Internet Natural Language Processing Techniques or
42 Qualitative Spatial Representation and Reasoning with the Region.. - Cohn, Bennett, Gooday, Gotts (1997)(Correct)
This paper surveys the work of the qualitative spatial reasoning group at the University of Leeds. The group has developed a number of logical calculi for representing and reasoning with qualitative... / of giving a semantics to natural language spatial expressions e.g. br region rather a point. Even in natural language the word point is not
41 Synchronous Tree-Adjoining Grammars - Shieber (1990)(Correct)
The unique properties of tree-adjoining grammars
(TAG) present a challenge for the application of
TAGs beyond the limited confines of syntax, for
instance, to the task of semantic interpretation or
au... / or automatic translation of natural language. We present a variant of br is to relate expressions of natural languages to their associated
41 Information Extraction as a Basis for High-Precision Text.. - Riloff, Lehnert (1994)(Correct)
We describe an approach to text classification that represents a compromise between
traditional word-based techniques and in-depth natural language processing.
Our approach uses a natural language pro... / techniques and in-depth natural language processing. Our approach br Our approach uses a natural language processing task called
40 A Maximum Entropy Approach to Adaptive Statistical Language Modeling - Rosenfeld (1996)(Correct)
An adaptive statistical languagemodel is described, which successfullyintegrates long distancelinguistic
information with other knowledge sources. Most existing statistical language models exploit onl... / and exploit regularities in natural language. In statistical language br application that processes natural language with incomplete knowledge.
40 An Open Agent Architecture - Cohen, Cheyer, Wang, Baeg (1994)(Correct)
The goal of this ongoing project is to develop an open agent architecture and accompanying user interface for networked desktop and handheld machines. The system we are building should support distrib... / the solving of a subgoal natural language vocabulary used by the br typed and soon handwritten natural language queries from the user and
40 A Performance Evaluation of Text Analysis Technologies - Lehnert, Sundheim (1991)(Correct)
This report describes the most
recent and most sophisticated of these evaluations, the Third Message Understanding
Conference (MUC-3) 1
This evaluation was sponsored by the Defense Research Projects
A... / to evaluate state-of-the-art natural language processing systems the br to bring together established natural language processing systems for the
39 Unsupervised Learning of Disambiguation Rules for Part of Speech.. - Brill (1995)(Correct)
In this paper we describe an unsupervised learning algorithm for automatically
training a rule-based part of speech tagger without using a manually tagged corpus. We
compare this algorithm to the Baum... / been applied to a number of natural language problems including part of br Darpa Workshop on Speech and Natural Language. Harriman N.Y. Brill and
38 Grammatical Trigrams: A Probabilistic Model of Link Grammar - Lafferty, Sleator, Temperley (1992)(Correct)
In this paper we present a new class of language models. This class derives from link grammar,
a context-free formalism for the description of natural language. We describe an algorithm for
determinin... / for the description of natural language. We describe an algorithm for br the relative entropy of natural language. Introduction
38 A Maximum Entropy Model for Prepositional Phrase Attachment - Adwait Ratnaparkhi (1994)(Correct)
this paper methods for constructing
statistical models for computing the probability of
attachment decisions. These models could be then integrated
into scoring the probability of an overall parse. We... / Introduction A parser for natural language must often choose between two br hinder the performance of most natural language parsers. References .
38 A Tourist Guide through Treewidth - Bodlaender (1993)(Correct)
A short overview is given of many recent results in algorithmic graph theory that deal with the notions treewidth, and pathwidth. We discuss algorithms that find tree-decompositions, algorithms that u... / . Natural language processing Kornai and Tuza br of this notion to natural language processing see
38 A Survey of Agent-Oriented Methodologies - Iglesias, Garijo, Gonzalez (1999)(Correct)
This article introduces the current agent-oriented methodologies. It discusseswhat approacheshave been followed (mainly extending existing objectoriented and knowledge engineering methodologies), th... / identification using natural language of the main roles played by
37 Evaluation of KQML as an Agent Communication Language - Mayfield, Labrou, Finin (1996)(Correct)
This chapter discusses the desirable features of languages and protocols
for communication among intelligent information agents. These desiderata
aredividedintosevencategories:form,content,semantics... / as event simulation applied natural language processing knowledge-based br primitives is often limited to natural language descriptions a
37 Formal and Computational Aspects of Natural Language Syntax - Rambow (1994)(Correct)
Formal and Computational Aspects of Natural Language Syntax Author: Owen Rambow Supervisors: Aravind K. Joshi and Anthony Kroch This thesis explores issues related to using a restricted mathematical f... / and Computational Aspects of Natural Language Syntax Ph.D. Dissertation br and Computational Aspects of Natural Language Syntax Owen Rambow A
37 A Neural Network Approach to Topic Spotting - Wiener, Pedersen, Weigend (1995)(Correct)
This paper presents an application of
nonlinear neural networks to topic spotting.
Neural networks allow us to model higherorder
interaction between document terms
and to simultaneously predict multip... / topics are present in a natural language document. More formally br In Proceedings of Speech and Natural Language Workshop pages -
36 An Algorithm for Generating Quantifier Scopings - Hobbs (1987)(Correct)
The syntactic structure of a sentence often manifests quite clearly the predicateargument
structure and relations of grammatical subordination. But scope dependencies
are not so transparent. As a resu... / has to face in constructing a natural language system but that simply have br a practice. A problem that many naturallanguage efforts have faced is the
36 Ellipsis and Higher-Order Unification - Dalrymple, Shieber, Pereira (1991)(Correct)
We present a new method for characterizing the interpretive possibilities generated
by elliptical constructions in natural language. Unlike previous analyses, which postulate
ambiguity of interpretati... / by elliptical constructions in natural language. Unlike previous analyses
35 Stochastic Attribute-Value Grammars - Abney (1997)(Correct)
Probabilistic analogues of regular and context-free grammars are wellknown
in computational linguistics, and currently the subject of intensive
research. To date, however, no satisfactory probabilisti... / of random fields to natural language was by Mark et al. The br also applies random fields to natural language processing. The application
35 Prepositional Phrase Attachment through a Backed-Off Model - Collins, Brooks (1995)(Correct)
Recent work has considered corpus-based or statistical approaches to the problem of prepositional phrase attachment ambiguity. Typically, ambiguous verb phrases of the form v np1 p np2 are resolved th... / of structural ambiguity in natural language. For example take the br the June DARPA Speech and Natural Language Workshop Hidden Valley
34 Induction of First-Order Decision Lists: Results on Learning the Past .. - Mooney (1995)(Correct)
This paper presents a method for inducing logic programs from examples that learns
a new class of concepts called first-order decision lists, defined as ordered lists of clauses
each ending in a cut. ... / the construction of natural-language parsers Zelle Mooney br incorporating morphology into natural language understanding systems which
34 Natural language processing for information retrieval - Lewis (1996)(Correct)
The paper summarizes the essential properties of document retrieval and reviews both conventional practice and research findings, the latter suggesting that simple statistical techniques can be effect... / Natural language processing for information br with a focus on the role of natural language processing. The paper also
33 A Survey of three Dialogue Models - Green (1986)(Correct)
This paper shows how the code for the user interface part of an interactive application can be automatically generated from an object-oriented specification formalism based on high-level Petri nets.... / formal and non-ambiguous such natural language informal requirements It br otherwise hard to describe in natural language. A transition of a PNO may
33 Experiments on Using Semantic Distances Between Words in Image.. - Smeaton, Quigley (1996)(Correct)
Traditional approaches to information retrieval are based
upon representing a user's query as a bag of query terms
and a document as a bag of index terms and computing a
degree of similarity between ... / combination of keywords a natural language statement or it can be the br pain and belly ache ffl natural language the vehicle with which the
33 Actions and Events in Interval Temporal Logic - Allen, Ferguson (1994)(Correct)
We present a representation of events and action based on interval temporal logic that is significantly more expressive and more natural than most previous AI approaches. The representation is motivat... / is motivated by work in natural language semantics and discourse br and prediction but also natural language understanding and
32 COLLAGEN: When Agents Collaborate with People - Rich, Sidner (1996)(Correct)
We take the position that autonomous agents, when they interact with people, should be governed by the same principles that underlie human collaboration. These principles come from research in computa... / learning without requiring natural language understanding by the agent.
32 An Efficient Probabilistic Context-Free Parsing Algorithm that.. - Stolcke (1995)(Correct)
this article can compute solutions to all four of these problems in a single framework,withanumber of additional advantagesoverpreviously presented isolated solutions. Most probabilistic parsers are b... / are widely used as models of natural language syntax. In their br clearly not a perfect model of natural language stochastic context-free
32 Lamarckian Learning in Multi-agent Environments - Grefenstette (1991)(Correct)
Genetic algorithms gain much of their power from
mechanisms derived from the field of population
genetics. However, it is possible, and in some
cases desirable, to augment the standard mechanisms
with... / are A flexible and natural language for expressing rules.
31 TREC and TIPSTER Experiments With INQUERY - James Callan (1995)(Correct)
INQUERY is a probablistic information retrieval system based upon a Bayesian
inference network model. This paper describes recent improvements to the system as
a result of participation in the TIPSTER... / based on similar evidence from natural language queries and user br versions of the query such as natural language and Boolean can be combined
31 Broad Agents - Bates, Loyall, Reilly (1991)(Correct)
The Oz project at Carnegie Mellon is developing
technology for dramatic virtual worlds.
1
One requirement
of such worlds is the presence of broad,
though perhaps shallow, agents. To support our
need... / its effects on behavior some natural language abilities especially br its effects on behavior some natural language abilities especially
31 Treewidth: Algorithmic techniques and results - Bodlaender (1998)(Correct)
This paper gives an overview of several results and techniques for graphs algorithms that compute the treewidth of a graph or that solve otherwise intractable problems when restricted graphs with boun... / Choleski factorization natural language processing see e.g. br and their application in natural language processing. Disc. Appl.
30 Updates and Counterfactuals - Grahne (1991)(Correct)
We study the problem of combining updates ---a special instance of theory change--- and counterfactual conditionals in propositional knowledgebases. Intuitively, an update means that the world describ... / implicative statements of natural language. Consider for instance the
29 Pattern Associativity and the Retrieval of Semantic Networks - Levinson (1992)(Correct)
p.
1011-1024, Wiley, New York, 1987.
[58] C. Stanfill and D. Waltz, Toward memory-based reasoning. Comm. of the ACM, 29(12), 12131228
(December 1986).
[59] E. H. Sussenguth Jr., A graph-theoretic alg... / A Knowledge-Based Approach to Natural Language Understanding Technical br are created in particular how natural language is parsed into conceptual
29 Question Answering from Frequently-Asked Question Files: Experiences.. - Robin Burke (1997)(Correct)
This technical report describes FAQ Finder, a natural language question-answering
system that uses files of frequently-asked questions as its knowledge base. Unlike AI
question-answering systems that ... / describes FAQ Finder a natural language question-answering system br is the question stated in natural language Ogden While the
29 Using Multiple Knowledge Sources for Word Sense Discrimination - McRoy (1992)(Correct)
This paper addresses the problem of how to identify the intended meaning of individual
words in unrestricted texts, without necessarily having access to complete representations
of sentences. To discr... / Many problems in applied natural language processing -including br Our goal has been a natural language system that can effectively
29 A Case-Based Approach to Knowledge Acquisition for Domain-Specific.. - Cardie (1993)(Correct)
This paper describes a case-based approach to knowledge
acquisition for natural language systems that simultaneously
learns part of speech, word sense, and concept activation
knowledge for all open cl... / to knowledge acquisition for natural language systems that simultaneously br been an increasing number of natural language systems that successfully
29 On the Knowledge Underlying Multimedia Presentations - Arens, Hovy, Vossers (1993)(Correct)
We address one of the problems at the heart of automated multimedia presentation
production and interpretation. The media allocation problem can be stated as follows:
how does the producer of a presen... / multiple modalities. Even natural language which is after all the most br within such units natural language and other human-oriented
29 Cardinality Restrictions on Concepts - Baader, Buchheit, Hollunder (1993)(Correct)
The concept description formalisms of existing terminological systems allow
the user to express local cardinality restrictions on the fillers of a particular
role. It is not possible, however, to intr... / systems such as natural language processing often rely on br and W. A. Woods. Research in natural language understanding annual
28 A Hierarchical Use Case Model with Graphical Representation - Regnell, Anderson, Bergstrand (1996)(Correct)
Use case modelling is gaining increasing interest in computer -based systems engineering, especially in the earliest stages of system development, where requirements are elicited, documented and valid... / the emerging unified method.Natural language is the main tool in most br requirements specification. Natural language gives freedom and expressive
28 Experiences with Selecting Search Engines using Meta-Search - Dreilinger (1997)(Correct)
Search engines are among the most useful and high profile resources on the Internet. The
problem of finding information on the Internet has been replaced with the problem of knowing
where search engin... / two important qualities of natural language text to perform accurate
28 Miniature Language Acquisition: A touchstone for cognitive science - Feldman, Lakoff, Stolcke, Weber (1990)(Correct)
Cognitive Science, whose genesis was interdisciplinary, shows signs of reverting to a disjoint collection of fields. This paper presents a compact, theory-free task that inherently requires an integra... / a subset of an arbitrary natural language from picture-sentence pairs. br the world. Computer vision and natural language processing are seen as
27 Comparative Experiments on Disambiguating Word Senses: An.. - Mooney (1996)(Correct)
This paper describes an experimental comparison
of seven different learning algorithms on the
problem of learning to disambiguate the meaning
of a word from context. The algorithms tested
include stat... / on Empirical Methods in Natural Language Processing br in empirical corpus-based natural language processing has explored a
27 Automatic Query Expansion Using SMART : TREC 3 - Buckley(Correct)
The Smart information retrieval project emphasizes completely automatic approaches to the understanding
and retrieval of large quantities of text. We continue our work in TREC 3, performing runs in th... / of words and expressions in natural-language texts and about the contexts br on disk as an inverted file. Natural language queries undergo the same
27 Natural Language Information Retrieval: TREC-3 Report - Strzalkowski, Carballo, Marinescu(Correct)
In this paper we report on the recent developments in NYU's natural language information retrieval system, especially as related to the 3rd Text Retrieval Conference (TREC-3). The main characteristic ... / Natural Language Information Retrieval Trec- br recent developments in NYU's natural language information retrieval system
27 Information Extraction Using Hidden Markov Models - Leek (1997)(Correct)
This thesis shows how to design and tune a hidden Markov model to extract factual information from a corpus of machine-readable English prose. In particular, the thesis presents a HMM that classifies ... / HMM that classifies and parses natural language assertions about genes being br In contrast with traditional natural language processing methods this
27 Natural Language Information Retrieval Trec-6 Report - Strzalkowski, Lin(Correct)
Natural language processing techniques may hold a tremendous potential for overcoming the inadequacies of purely quantitative methods of text information retrieval, but the empirical evidence to sup... / Natural Language Information Retrieval Trec- br NJ Abstract. Natural language processing techniques may
26 Committee-Based Sampling For Training Probabilistic Classifiers - Dagan, Engelson (1995)(Correct)
In many real-world learning tasks, it is expensive
to acquire a sufficient number of labeled
examples for training. This paper proposes
a general method for efficiently training
probabilistic classifi... / the task of tagging words in natural language sentences with br in the area of statistical natural language and text processing. In this
26 The Zeno Argumentation Framework - Gordon (1997)(Correct)
The Zeno Argumentation Framework is a formal model of argumentation
based on the informal models of Toulmin and Rittel.
Its main feature is a labelling function using arguments to compute
heuristic in... / graphs can contain arbitrary natural language expressions and other forms
25 An Ontology of Meta-Level Categories - Guarino (1994)(Correct)
We focus in this paper on some meta-level ontological
distinctions among unary predicates,
like those between concepts and assertional
properties. Three are the main contributions of
this work, mostly... / since we are constantly using natural language words within our formulas br since words are ambiguous in natural language it may be important to tag
25 Collaborating on Referring Expressions - Heeman, Hirst (1995)(Correct)
This paper presents a computational model of how conversational participants collaborate in
order to make a referring action successful. The model is based on the view of language as
goal-directed beh... / of surface speech actions not natural language strings. Finally although br paradigm can be applied to natural language processing. The actions in
25 An Association Thesaurus for Information Retrieval - Jing (1994)(Correct)
Although commonly used in both commercial and experimental information retrieval
systems, thesauri have not demonstrated consistent benefits for retrieval performance, and
it is difficult to construct... / can be accessed through natural language queries in INQUERY an br on inference networks using natural language queries. Adding phrases
25 Automatic Extraction of Subcategorization from Corpora - Briscoe, Carroll (1997)(Correct)
We describe a novel technique and implemented system for constructing a subcategorization dictionary from textual corpora. Each dictionary entry encodes the relative frequency of occurrence of a compr... / E. . Large lexicons for natural language processing utilising the br Lexicography for Natural Language Processing. Longman
24 String Variable Grammar: A Logic Grammar Formalism For The Biological .. - Searls (1993)(Correct)
this paper, we present a generalized form of SVG, which supports additional
biologically-relevant operations by going beyond homomorphisms, instead
uniformly applying substitutions in either a forward... / well-suited to phenomena in natural language. We have proposed an br as varied as those in natural language. Clearly any attempt to
24 A Survey of Multilingual Text Retrieval - Oard, Dorr (1996)(Correct)
This report reviews the present state of the art in selection of texts in one language
based on queries in another, a problem we refer to as "multilingual" text retrieval.
Present applications of mult... / formulated by a human using natural language regardless of the language br accept queries expressed in natural language rather than as a boolean
24 Learning Maps for Indoor Mobile Robot Navigation - Thrun, Bücken (1998)(Correct)
Autonomous robots must be able to learn and maintain models of their environments.
Research on mobile robot navigation has produced two major paradigms
for mapping indoor environments: grid-based and ... / planner problem solver natural language Gamma planning
24 Natural Language Processing With Modular PDP Networks and Distributed .. - Miikkulainen, Dyer (1991)(Correct)
An approach to connectionist natural language processing is proposed, which is based on hierarchically
organized modular Parallel Distributed Processing (PDP) networks and a central lexicon of
distrib... / Natural Language Processing With Modular PDP br An approach to connectionist natural language processing is proposed which
23 Goals for Concept Representation in the GALEN project - Rector (1993)(Correct)
The GALEN project aims to develop language
independent concept representation systems as the
foundations for the next generation of multilingual
coding systems. Traditional coding schemes have
reached... / bibliographic retrieval and natural language processing. BACKGROUND
23 Mining Association Rules in Multiple Relations - Dehaspe (1997)(Correct)
The application of algorithms for efficiently generating association
rules is so far restricted to cases where information is put together
in a single relation. We describe how this restriction can ... / We apply Warmr to the natural language processing task of mining
23 A Plan-Based Model for Response Generation in Collaborative.. - Chu-Carroll (1994)(Correct)
This paper presents a plan-based architecture for response
generation in collaborative consultation dialogues, with emphasis
on cases in which the system (consultant) and user
(executing agent) disagr... / attempts to modify it and natural language utterances are generated as br causes the system to generate natural language utterances to accomplish the
23 Speech Recognition with Dynamic Bayesian Networks - Zweig, Russell (1998)(Correct)
Dynamic Bayesian networks (DBNs) are a useful tool
for representing complex stochastic processes. Recent
developments in inference and learning in DBNs allow
their use in real-world applications. In t... / the number of words in a natural language is large it is impossible
23 Exploring the Symbolic/Subsymbolic Continuum: A Case Study of RAAM - Blank (1992)(Correct)
this paper.
7 unknown Exploring the Symbolic/Subsymbolic Continuum: A Case
Study of RAAM
Douglas S. Blank (blank@iuvax.cs.indiana.edu)
Lisa A. Meeden (meeden@iuvax.cs.indiana.edu)
James B. Marshall (m... / in representations for natural language Port and van Gelder br of the sentences. We chose natural language as the domain for these
23 Improving the Use Case Driven Approach to Requirements Engineering - Regnell, al. (1995)(Correct)
This paper presents the idea of Usage Oriented Requirements
Engineering, an extension of Use Case Driven Analysis.
The main objective is to achieve a requirements
engineering process resulting in a mo... / Use cases are expressed in natural language with terms from the problem br some typical problems with natural language descriptions all the use
23 The Expressiveness of a Family of Finite Set Languages - Immerman (1991)(Correct)
In this paper we characterise exactly the complexity of a set based database
language called SRL, which presents a unified framework for queries and updates.
By imposing simple syntactic restrictions ... / are interested in devising a natural language whose complexity is clear br Question . Is there a natural language that expresses exactly the
23 A Pointless Theory of Space Based On Strong Connection and Congruence - Borgo, Guarino, Masolo (1996)(Correct)
We present a logical theory of space where only
tridimensional regions are assumed in the
domain. Three distinct primitives are used to
describe their mereological, topological and
morphological prope... / as robot navigation or natural language understanding. Besides br more oriented towards natural language applications like Aurnague
23 Contrary-to-duty obligations - Prakken (1996)(Correct)
We investigate under what conditions contrary-to-duty (CTD) structures lacking
temporal and action elements can be given a coherent reading. We argue, contrary
to some recent proposals, that CTD is no... / to be inconsistent in their natural language formulation. In section br of the ambiguity of many natural-language examples. Instead we will
22 Sri International Fastus System Muc-6 Test Results And Analysis - Appelt (1995)(Correct)
This paper will describe the version of the FASTUS system employed in MUC-6 and highlight the innovations that distinguish it from previous versions described in the literature. SRI used the FASTUS sy... / technologies in constrained natural-language understanding tasks. The br is typically expressed in natural language. Unfortunately this ideal is
22 A Survey of Information Retrieval and Filtering Methods - Faloutsos, Oard (1996)(Correct)
We survey the major techniques for information retrieval. In the first part, we provide an overview of the traditional ones (full text scanning, inversion, signature files and clustering). In the seco... / include semantic information natural language processing latent semantic br syntactic information and natural language processing in general b
22 A Common LISP Hypermedia Server - Mallery (1994)(Correct)
A World-Wide Web (WWW) server was implemented in Common LISP in order to
facilitate exploratory programming in the global hypermedia domain and to provide access to complex
research programs, partic... / inductive rule learning and natural-language question answering. br automatic rule induction and natural- language question answering.
22 Aggregate and mixed-order Markov models for statistical language.. - Saul, Pereira (1997)(Correct)
We consider the use of language models
whose size and accuracy are intermediate
between different order n-gram models.
Two types of models are studied in particular.
Aggregate Markov models are classb... / The simplest models of natural language are n- gram Markov br Class-based n-gram models of natural language. Computational Linguistics
22 Emergent Adaptive Lexicons - Steels (1996)(Correct)
The paper reports experiments to test the hypothesis
that language is an autonomous evolving
adaptive system maintained by a group of distributed
agents without central control. The experiments
show h... / several characteristics of natural language lexicons such as polysemy br None of the properties of a natural language such as hierarchical
22 DATR: A Language for Lexical Knowledge Representation - Evans, Gazdar (1996)(Correct)
this paper we shall distinguish them by a simple case convention -- node names start with an uppercase letter, atoms do not. 5 This is an approximation since it ignores the role of global contexts -- ... / research on the design of natural language lexicons has made use of br representation languages for natural language lexicons has thus made use of
22 Practical Unification-based Parsing of Natural Language - Carroll (1993)(Correct)
K SERC, and SERC / DTI-IED project
4/1/1261 `Extensions to the Alvey Natural Language Tools'.
Summary
The thesis describes novel techniques and algorithms for the practical parsing of realistic Natu... / Unification-based Parsing of Natural Language John Andrew Carroll br other members of the Alvey Natural Language Tools ANLT projects for
22 Adaptive Provision of Evaluation-Oriented Information: Tasks and.. - Jameson, Schäfer, Simons, Weis (1995)(Correct)
Evaluation-oriented information provision is a function performed by many systems that serve as personal assistants, advisors, or sales assistants. Five general tasks are distinguished which need to b... / three systems use some form of natural language. There are also large br function corresponding to a natural language formulation like quite
22 Arc-Consistency and Arc-Consistency Again - Bessière, Cordier (1994)(Correct)
There is no need to show the importance of arc-consistency in Constraint Networks. Mohr and Henderson [8] have proposed AC-4, an algorithm having an optimal worst-case time complexity. But it has two ... / reasoning and more recently natural language parsing. The problem of the
21 An Experiment in the Design of Software Agents - Kautz, Selman, Coen, Ketchpel.. (1994)(Correct)
We describe a bottom-up approach to the design of software agents. We built and tested an agent system that addresses the real-world problem of handling the activities involved in scheduling a visitor... / as understanding unrestricted natural language. After considering a number br considered various forms of natural language input instead of forms.
21 Mistake-Driven Learning in Text Categorization - Dagan (1997)(Correct)
Learning problems in the text processing
domain often map the text to a space
whose dimensions are the measured features
of the text, e.g., its words. Three
characteristic properties of this domain ar... / Learning problems in the natural language and text processing domains
21 Applying Winnow to Context-Sensitive Spelling Correction - Golding, Roth (1996)(Correct)
Multiplicative weight-updating algorithms
such as Winnow have been studied extensively
in the COLT literature, but only recently
have people started to use them in
applications. In this paper, we appl... / algorithm to a task in natural language context-sensitive spelling br of this task and related natural language tasks for Machine Learning
21 Coreference and Modality - Groenendijk (1996)(Correct)
this paper is devoted to an analysis of a specific problem
area, which is not only of interest descriptively, but which also presents an
interesting theoretical challenge.
The descriptive area is that... / this area began to think about natural language processing they quite br in Vermeulen to appear b. Natural language is not the primary target of
21 Interactive Assessment of User Preference Models: The Automated.. - Linden, Hanks, Lesh (1997)(Correct)
This paper presents the candidate/critique model of interactive problem solving,
in which an automated problem solver communicates candidate solutions to the user and
the user critiques those soluti... / . In that case a free-form natural-language dialogue allows solution br do not attempt to implement a natural language interface we would still
20 The Saphira Architecture: A Design for Autonomy - Konolige, Myers, Ruspini, Saffiotti (1997)(Correct)
Journal of Experimental and Theoretical Artificial Intelligence (JETAI) 9, 1997, 215-235.
Special issue on Architectures for Physical Agents.
Mobile robots, if they areto perform useful tasks andbecom... / here by starting to integrate natural language input and perceptual br strongly influenced by the Natural Language Understanding community
20 Machine Learning for Information Extraction in Informal Domains - Freitag (1998)(Correct)
Information extraction, the problem of generating structured summaries of human-oriented text documents, has been studied for over a decade now, but the primary emphasis has been on document collectio... / the hand-tuning of general natural language processing systems to a br The complementary endeavor of natural language processing has sought to
20 A Linear-Programming Approach to Temporal Reasoning - Jonsson, Bäckström (1996)(Correct)
We present a new formalism, Horn Disjunctive Linear Relations (Horn DLRs), for reasoning about temporal constraints. We prove that deciding satisfiability of sets of Horn DLRs is polynomial by exhibit... / elsewehere such as planning natural language processing diagnosis time
20 The Chinook Hardware/Software Co-Synthesis System - Pai Chou (1995)(Correct)
Embedded systems are becoming more commonplace and are being designed by larger numbers
of designers with ever tighter constraints on design time. Unfortunately, computer aided
design tools for embedd... / informally using a mixture of natural language documents pseudo-code and
20 Learning Collection Fusion Strategies for Information Retrieval - Towell (1995)(Correct)
In this paper we describe an Information Retrieval
problem called collection fusion. The collection
fusion problem is to maximize the number
of relevant natural language documents retrieved
given: a n... / the number of relevant natural language documents retrieved given a br documents retrieved given a natural language query multiple collections
20 Noun Homograph Disambiguation Using Local Context in Large Text.. - Hearst (1991)(Correct)
This paper describes an accurate, relatively inexpensive method for the disambiguation of noun
homographs using large text corpora. The algorithm checks the context surrounding the target noun
against... / to multi-million word corpora natural language processing techniques must br complex mechanisms used by natural language processing techniques e.g.
20 A Hierarchical Dirichlet Language Model - MacKay, Peto (1994)(Correct)
We discuss a hierarchical probabilistic model whose predictions are similar to those of the popular language modelling procedure known as `smoothing'. A number of interesting differences from smoothin... / Natural Language Engineering -
20 Reasoning about Information Change - Gerbrandy, Groeneveld (1987)(Correct)
In this paper, we have combined techniques from epistemic and dynamic logic to arrive at a logic for describing multi-agent information change. The key concept of dynamic semantics is that the meaning... / the formal semantics of natural language and computer science. The
19 DPOCL: A Principled Approach to Discourse Planning - Young (1994)(Correct)
Research in discourse processing has identified two representational requirements for discourse planning systems. First, discourse plans must adequately represent the intentional structure of the utte... / a series of sentences in a natural language. Recent work has shown that br plan into a series of natural language utterances. . DPOCL's
19 An Overview of Strategies for Neurosymbolic Integration - Hilario (1995)(Correct)
At the crossroads of symbolic and neural
processing, researchers have been actively
investigating the synergies that might be
obtained from combining the strengths of
these two paradigms. Neurosymboli... / and Kurfess natural language understanding Bookman br Symbolic neuroengineering for natural language processing A multilevel
19 Light-years from Lena: Video and Image Libraries of the Future - Picard (1995)(Correct)
The average consumer with a personal computer
will soon have access to the world's collections
of digital video and images. However, the theory
and tools that facilitate browsing, querying,
retrieval,... / script and story knowledge natural language common sense
19 Maximum Entropy Models For Natural Language Ambiguity Resolution - Ratnaparkhi (1998)(Correct)
This thesis demonstrates that several important kinds of natural language ambiguities can be resolved to state-of-the-art accuracies using a single statistical modeling technique based on the principl... / Maximum Entropy Models For Natural Language Ambiguity Resolution Adwait br to be the best way to approach natural language processing and also gave me
19 Natural Language Syntax and First Order Inference - McAllester, Givan (1992)(Correct)
We have argued elsewhere that first order inference can be made more
efficient by using non-standard syntax for first order logic. In this paper we define
a syntax for first order logic based on the... / Natural Language Syntax and First Order br based on the structure of natural language under Montague semantics. We
19 Generating Summaries of Multiple News Articles - Mckeown (1995)(Correct)
So That Nobody Has To Go To School If They Don't Want To by Roger Sipher A decline in standardized test scores is but the most recent indicator that American education is in trouble. One reason for th... / Abstract We present a natural language system which summarizes a br systems. Keywords Natural language summarization Natural
19 An Empirical Study of Automated Dictionary Construction for.. - Riloff (1996)(Correct)
this paper, we describe experiments with AutoSlog in
two additional domains: joint ventures and microelectronics. We
compare the performance of AutoSlog across the three domains,
discuss the lessons l... / UT A primary goal of natural language processing researchers is to br to develop a knowledge-based natural language processing NLP system that
19 Information extraction for semi-structured documents - Smith, Lopez (1997)(Correct)
this paper constitutes a suitable basis for building an effective solution to extracting information from semi-structured documents for two principal reasons. First, it provides an extensible architec... / us to avoid the use of complex natural language understanding techniques br research efforts from a natural language processing perspective e.g.
19 Bayesian Grammar Induction for Language Modeling - Stanley Chen (1995)(Correct)
We describe a corpus-based induction algorithm
for probabilistic context-free grammars.
The algorithm employs a greedy
heuristic search within a Bayesian framework,
and a post-pass using the InsideOut... / the largest practical n for natural language is three and many br and many dependencies in natural language occur beyond a three-word
19 Word Sense Disambiguation and Information Retrieval - Sanderson (1997)(Correct)
It has often been thought that word sense ambiguity is a cause of poor performance in Information Retrieval
(IR) systems. The belief is that if ambiguous words can be correctly disambiguated, IR perfo... / a computer has to process natural language ambiguity is a problem. For br In Strategies for Natural Language Processing Lehnert WG
19 Disambiguation of Proper Names in Text - Wacholder, Ravin, Choi (1997)(Correct)
Identifying the occurrences of proper
names in text and the entities they refer to
can be a difficult task because of the manyto
-many mapping between names and their
referents. We analyze the types o... / of the th Applied Natural Language Processing Conference br Proper Name Identification in Natural Language Processing Text processing
18 A Survey of the Eighth National Conference on Artificial.. - Cohen (1991)(Correct)
A survey of 150 papers from the Proceedings of the Eighth National Conference on
Artificial Intelligence (AAAI-90) shows that AI research follows two methodologies,
each incomplete with respect to the... / humans encounter such as natural language understanding cross-country br to perform tasks such as natural language understanding in real time
18 Ontology Development for Machine Translation: Ideology and Methodology - Mahesh (1996)(Correct)
In the Mikrokosmos approach to knowledge-based machine translation, lexical representation of word meanings as well as text meaning representation is grounded in a broad-coverage ontology of the world... / in knowledge representation natural language semantics and software br value in almost every stage of natural language processing and linguistic
18 PARADISE: A Framework for Evaluating Spoken Dialogue Agents - Walker, Litman, Kamm, Abella (1997)(Correct)
This paper presents PARADISE (PARAdigm for DIalogue System Evaluation), a general framework for evaluating spoken dialogue agents. The framework decouples task requirements from an agent's dialogue be... / speech recognition and natural language processing have made it br Proceedings of the Speech and Natural Language Workshop pages - .
18 Contextual Word Similarity and Estimation from Sparse Data - Dagan, Marcus, al. (1995)(Correct)
In recent years there is much interest in word cooccurrence relations, such as
n-grams, verb-object combinations, or cooccurrence within a limited context.
This paper discusses how to estimate the lik... / corpus based approaches for natural language and speech processing. br corpus based approaches for natural language and speech processing. Many
18 Prior Learning and Gibbs Reaction-Diffusion - Zhu, Mumford (1997)(Correct)
This article addresses two important themes in early visual computation: first it
presents a novel theory for learning the universal statistics of natural images -- a prior
model for typical cluttered... / entropy have also been used in natural language modeling In this paper br maximum entropy approach to natural language processing Computational
17 Intelligent Interfaces As Agents - Chin (1991)(Correct)
An intelligent interface cannot just respond passively to its user's commands and queries. It must be able
to take the initiative in order to volunteer information, correct user misconceptions, or rej... / of UC UNIX Consultant a natural-language system that helps the user br be agents and will describe a natural-language interface that implements
17 Personality-Rich Believable Agents That Use Language - Bryan Loyall (1997)(Correct)
We are studying how to create believable agents that
perform actions and use natural language in interactive,
animated, real-time worlds. Believable agents are autonomous
agents that have specific, ri... / that perform actions and use natural language in interactive animated br believable agents to support natural language text generation. These
17 Context and Page Analysis for Improved Web Search - Lawrence, Giles (1998)(Correct)
NEC Research Institute has developed a metasearch engine that improves the efficiency of Web searches by downloading and analyzing each document and then displaying results that show the query terms i... / engines that list support for natural language queries. As the amount of br time series prediction and natural language. His awards include an NEC
17 The Power of Amnesia: Learning Probabilistic Automata with Variable.. - Ron, SINGER, TISHBY (1996)(Correct)
We propose and analyze a distribution learning algorithm for variable memory length
Markov processes. These processes can be described by a subclass of probabilistic finite automata
which we name Pr... / in human communication such as natural language handwriting and speech br the last stage employs natural-language analysis techniques to
17 Information Extraction: Techniques and Challenges - Grishman (1997)(Correct)
this paper
we shall use a narrower definition: the identification of instances of a particular
class of events or relationships in a natural language text, and the extraction of
the relevant arguments... / events or relationships in a natural language text and the extraction of br what is possible with current natural language processing technology and
17 Adaptive Sentence Boundary Disambiguation - Palmer, Hearst (1994)(Correct)
Labeling of sentence boundaries is a necessary prerequisite for many natural language processing tasks, including part-ofspeech tagging and sentence alignment. End-of-sentence punctuation marks are am... / prerequisite for many natural language processing tasks including br prerequisite for many natural language processing NLP tasks
17 Learning to Resolve Natural Language Ambiguities: A Unified Approach - Roth (1998)(Correct)
We analyze a few of the commonly used statistics based
and machine learning algorithms for natural language
disambiguation tasks and observe that they can be recast
as learning linear separators in th... / AAAI- Learning to Resolve Natural Language Ambiguities A Unified br learning algorithms for natural language disambiguation tasks and
17 COLLAGEN: A Collaboration Manager for Software Interface Agents - Rich (1998)(Correct)
We have implemented an application-independent collaboration manager, called Collagen,
based on the SharedPlan theory of discourse, and used it to build a software interface
agent for a simple air tra... / assistance without requiring natural language understanding. A key benefit br assistance without requiring natural language understanding. A key benefit
17 Multi-party Specification - Finkelstein, Fuks (1989)(Correct)
This paper examines a formal model of how specifications can be constructed from multiple viewpoints and presents some tools to support this approach. The development of specifications is presented as... / are built and documented -in natural language -is a well understood way of br example Allwood the natural language processing tradition in
17 Document Filtering With Inference Networks - Callan (1996)(Correct)
Although statistical retrieval models are now accepted
widely, there has been little research on how to adapt them
to the demands of high speed document filtering. The problems
of document retrieval a... / specified by a user in either natural language or a structured query br in either a query language or natural language. InRoute shares INQUERY's
17 Domain-Specific Knowledge Acquisition For Conceptual Sentence Analysis - Cardie (1994)(Correct)
DOMAIN-SPECIFIC KNOWLEDGE ACQUISITION
FOR CONCEPTUAL SENTENCE ANALYSIS
SEPTEMBER 1994
CLAIRE CARDIE, B.S., YALE UNIVERSITY
M.S., UNIVERSITY OF MASSACHUSETTS AMHERST
Ph.D., UNIVERSITY OF MASSACHUSETTS ... / and informed views of natural language processing and artificial br rapidly changing the field of natural language processing NLP from one
17 An Overview of Cooperative Answering - Gaasterland, al. (1992)(Correct)
Databases and information systems are often hard to use because they do not explicitly attempt to cooperate
with their users. Direct answers to database and knowledge base queries may not always be th... / along with relevant work in natural language dialogue systems database br Query Answer Systems . Natural Language Interfaces
16 Three studies of grammar-based surface parsing of unrestricted.. - Voutilainen (1994)(Correct)
Three studies of grammar-based surface parsing of unrestricted English text
Voutilainen, Atro Tapio
University of Helsinki, SF
The dissertation addresses the design of parsing grammars for automatic s... / the grammar-based approach to natural language parsing thus also br parsing description of a natural language for the purposes of
16 The Challenge of Spoken Language Systems: Research Directions for the .. - Cole (1995)(Correct)
A spoken language system combines speech recognition, natural language processing and human interface technology. It functions by recognizing the person's words, interpreting the sequence of words to ... / and Kathy McKeown . Natural Language Response Generation Kathy br combines speech recognition natural language processing and human
16 Automatic Detection of Feature Interactions in Temporal Logic - Blom, Bol, Kempe (1995)(Correct)
this paper; we give some hints on this topic in the final section. In the same section,
we discuss how our current view of the system should be refined in order to arrive at the
distributed telecommun... / example a specification in natural language might say If someone is br known problem for formalising natural language in logic. The word someone'
16 Sources of Flexibility in Dynamic Hypertext Generation - Knott (1996)(Correct)
Dynamic hypertext' is hypertext which is automatically
generated at the point of need. A
number of NLG systems have now been developed
to operate within a hypertext environment;
and now that these sy... / As a central objective of Natural Language Generation NLG is on-line br and monuments. It supports natural language input and output and
16 Learning Dictionaries for Information Extraction by Multi-Level.. - Riloff, Jones (1999)(Correct)
Information extraction systems usually require two
dictionaries: a semantic lexicon containing domainspecific
phrases and a dictionary of extraction patterns
for the domain. We present a multi-level b... / number A Keywords Natural language processing Statistical or br or corpus-based methods Natural language processing Information
16 Incorporating Advice into Agents that Learn from Reinforcements - Maclin (1994)(Correct)
Learning from reinforcements is a promising approach
for creating intelligent agents. However, reinforcement
learning usually requires a large number of training
episodes. We present an approach that ... / its advice in some quasi-natural language using terms about the br Due to the complexities of natural language processing we require that
16 Network-Based Information Brokers - Fikes, Engelmore, Farquhar, Pratt (1995)(Correct)
ions and assumptions that will enable the agent to retrieve information that is relevant to a query. . Methods for appropriately combining and summarizing retrieved information. Building such brokers ... / a logic or semi-structured natural language documents on a document
15 A Policy Based Role Object Model - Lupu, Sloman (1997)(Correct)
Enterprise roles define the duties and responsibilities of the individuals which are assigned to them. This paper introduces a framework for the management of large distributed systems which makes use... / are usually specified in natural language in terms of groups of
15 A Situated Ontology for Practical NLP - Mahesh, Nirenburg (1995)(Correct)
A situated ontology is a world model used as a computational resource for solving a particular set of problems.
It is treated as neither a "natural" entity waiting to be discovered nor a purely theore... / et al. In the field of natural language processing NLP there is br an ontology to facilitate natural language interpretation and
15 Representations and Solutions for Game-Theoretic Problems - Koller, Pfeffer (1997)(Correct)
A system with multiple interacting agents (whether artificial or human) is often best analyzed
using game-theoretic tools. Unfortunately, while the formal foundations are well-established,
standard co... / is typically described in natural language by presenting its rules. For br is typically described in natural language by presenting its rules.
15 Robust Stochastic Parsing Using the Inside-Outside Algorithm - Briscoe, Waegner (1992)(Correct)
this paper, we discuss the application of the Viterbi algorithm and the Baum-Welch algorithm (in wide use for speech recognition) to the parsing problem and describe a recent experiment designed to pr... / on Probabilistically-Based Natural Language Processing Techniques San br the grammatical sentences of a natural language constitute a well-formed set
15 Context and Structure in Automated Full-Text Information Access - Hearst (1994)(Correct)
s
Service. Journal of Chemical Information and Computer Sciences 15.226--233.
BIBLIOGRAPHY 123
MACKINLAY, JOCK, 1986. Automatic design of graphical presentations. Stanford University
dissertation. T... / on Discourse Structure in Natural Language Understanding and br in problem solving and natural language understanding. Cognitive
15 Lexical Ambiguity and Information Retrieval - Krovetz (1992)(Correct)
Lexical ambiguity is a pervasive problem in natural language processing. However, little
quantitative information is available about the extent of the problem, or about the impact
that it has on infor... / is a pervasive problem in natural language processing. However little br Artificial Intelligence Natural Language Processing text
15 Incremental Generation for Real-Time Applications - Kilger, Finkler (1995)(Correct)
The acceptance of natural language generation systems strongly depends on
their capability to facilitate the exchange of information with human users. Current
generation systems consider the influence... / Abstract The acceptance of natural language generation systems strongly br of software systems in natural language processing e.g.
15 Building Probabilistic Models for Natural Language - Chen (1996)(Correct)
Building models of language is a central task in natural language processing. Traditionally,
language has been modeled with manually-constructed grammars that describe which
strings are grammatical an... / Probabilistic Models for Natural Language A thesis presented by br language is a central task in natural language processing. Traditionally
15 Multimodal User Interfaces in the Open Agent Architecture - Moran, Cheyer, Julia, Martin (1997)(Correct)
The design and development of the Open Agent Architecture
(OAA)
1
system has focused on providing access to agentbased
applications through an intelligent, cooperative, distributed,
and multimodal a... / speech gesture handwriting natural language INTRODUCTION A major br raw text or interpreted by a natural language understanding agent. There
15 A Connectionist Parser with Recursive Sentence Structure and Lexical.. - Berg (1992)(Correct)
In order to be taken seriously, connectionist natural language processing systems must be able to parse syntactically complex sentences. Current connectionist parsers either ignore structure or impose... / taken seriously connectionist natural language processing systems must be br of connectionist models of natural language processing NLP is the rich
15 Noise Reduction in a Statistical Approach to Text Categorization - Yang (1995)(Correct)
This paper studies noise reduction for computational efficiency improvements in a statistical learning method for text categorization, the Linear Least Squares Fit (LLSF) mapping. Multiple noise reduc... / or redundancy property of natural language texts not every word or br and operative reports in natural language texts written by physicians.
15 A Generic Platform for Addressing the Multimodal Challeng - Nigay, Coutaz (1995)(Correct)
Multimodal interactive systems support multiple
interaction techniques such as the synergistic use of speech
and direct manipulation. The flexibility they offer results in
an increased complexity that... / MATIS include speech written natural language graphic input and output br couple microphone pseudo natural language NLwhere NL is defined by a