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.
13896.9 The Rhetorical Parsing, Summarization, and Generation of Natural.. - Marcu (1997)(Correct)
This thesis is an inquiry into the nature of the high-level, rhetorical structure of unrestricted
natural language texts, computational means to enable its derivation, and two applications
(in automat... / most salient phrases. Information-extraction-based systems
7831.6 Database Techniques for the World-Wide Web: A Survey - Florescu, Levy, Mendelzon (1998)(Correct)
The primary goal of this survey is to classify the different tasks to which database concepts have been applied, and to emphasize the technical innovations that are required to do so. We focus on thre... / collection of web sites. Information extraction and integration Certain br Ashish and Craig A. Knoblock. Wrapper generation for semi-structured
7090.0 Machine Learning and Natural Language Processing - Marquez (2000)(Correct)
In this report, some collaborative work between the fields of Machine Learning (ML) and Natural Language Processing (NLP) is presented. The document is structured in two parts. The first part includes... / and robust parsing information extraction and retrieval automatic
6766.5 Complexity of Lexical Descriptions and its Relevance to Partial.. - Bangalore (1997)(Correct)
Complexity of Lexical Descriptions and its Relevance to Partial Parsing
Srinivas Bangalore
Supervisor: Aravind K. Joshi
In this dissertation, we have proposed novel methods for robust parsing that int... / part-of-speech tags. In an information extraction task supertags are used
5210.3 Relational Learning Techniques for Natural Language Information.. - Califf (1998)(Correct)
vii
Chapter 1 Introduction 1
1.1 Organization of Dissertation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
Chapter 2 Background 5
2.1 Information Extraction . . . . . . . . . .... / for Natural Language Information Extraction Mary Elaine Califf
5068.9 An algorithm toolbox for on-line cursive script recognition - Powalka(Correct)
This thesis deals with algorithms for on-line cursive script recognition. A novel concept
of a recognition toolbox is introduced. Algorithms applicable to various aspects of the
recognition are invest... / two approaches to zoning information extraction are applied Guerfali
4491.9 Techniques For Automatic Digital Video Composition - Ahanger (1999)(Correct)
Recent developments in digital technology have enabled a class of video-based
applications that were not previously viable. However, digital video production systems
face the challenge of accessing th... / . . Information Extraction and Representation .
4358.0 Retrieval of Passages for Information Reduction - Daniels (1996)(Correct)
Information Retrieval (IR) typically retrieves entire documents in response to a user's information
need. However, many times a user would prefer to examine smaller portions of a
document. One example... / we could save an automated information extraction system from processing an
4265.3 Generating Natural Language Summaries from Multiple On-Line Sources.. - Radev (1999)(Correct)
information,
highlighting agreements and contradictions among sources on the same topic.
We have developed novel techniques and algorithms for combining data from
multiple sources at the conceptual l... / coupled with appropriate information extraction technology generates br using linguistic knowledge extraction. Information Processing and
4259.8 Information Extraction for Run-time Formal Analysis - Kim (2001)(Correct)
The significance of software systems has rapidly increased. The assurance of software systems has
become a critical requirement of the information age. Formal verification on the design of a system
an... / Information Extraction for Run-time Formal
3978.1 Document Image Compression and Analysis - Kia (1997)(Correct)
Image compression usually considers the minimization of storage space as its main
objective. It is desirable, however, to code images so that we have the ability to
process the resulting representatio... /
3930.5 Combining Artificial Intelligence and Databases for Data Integration - Levy (1998)(Correct)
Data integration is a problem at the intersection of the fields of Artificial Intelligence and
Database Systems. The goal of a data integration system is to provide a uniform interface to a
multitude ... / Weld. Wrapper induction for information extraction. In Proceedings of the br Ashish and Craig A. Knoblock. Wrapper generation for semi-structured internet
3862.0 A Metrics-Based Approach To The Automated Identification Of.. - Etzkorn (1997)(Correct)
Software reuse has been a long term goal of software developers. This goal has been rather elusive, but the widespread use of the object-oriented paradigm and other innovations in software development... / Sublanguages . . . Information Extraction Systems . . Semantic
3574.3 Using Dia-MoLE For Unsupervised Learning Of Domain-Specific Dialogue.. - Möller(Correct)
This report introduces DIA-MOLE, a tool that supports an engineering-oriented approach
towards dialogue modelling for a spoken-language interface. Our approach is applied to the domain of
appointmen... / reported on discourse-level information extraction Leh . . .
3495.3 Wrapper Induction: Efficiency and Expressiveness - Kushmerick (2000)(Correct)
The Internet presents numerous sources of useful information---telephone directories, product
catalogs, stock quotes, event listings, etc. Recently, many systems have been built that automatically
gat... / reserved. Keywords Information extraction Wrapper induction br C. Knoblock Semi-automatic wrapper generation for Internet information
3457.4 Towards Learning Dialogue Structures from Speech Data and Domain.. - Möller(Correct)
This paper introduces an engineering-oriented approach towards dialogue modelling. While
dialogue models in existing dialogue systems usually are manually coded, or at least the
data on which they are... / on discourse level information extraction Leh One possible
3235.0 Cyclostationary And Higher-Order Statistical Signal Processing.. - McCormick (1998)(Correct)
In this thesis the problem of monitoring the condition of machinery is addressed
using cyclostationary and higher-order statistical analysis of vibration signals.
These have the potential to provide i... / disrupts more traditional information extraction procedures such as power
3224.3 Instructable and Adaptive Web-Agents which Learn to Categorize and.. - Eliassi-Rad (1999)(Correct)
this
paper. Section 3 describes our internal representation of Web pages, the major predicates in
our advice language, how advice is mapped into neural networks, the mechanisms for re ning
advice base... / . . Information Extraction . br text. . Information Extraction Information extraction IE
3181.4 A Computational Theory Of Vocabulary Expansion - Ehrlich, Rapaport (1997)(Correct)
This project concerns the development and implementation of a computational theory of how
human readers and other natural-language-understanding systems can automatically expand
their vocabulary by de... / message-processing or information-extraction systems need to be
3064.3 A Machine Learning Approach to POS Tagging - Màrquez, Padró, Rodríguez (1998)(Correct)
We have applied the inductive learning of statistical decision trees and relaxation
labelling to the Natural Language Processing (nlp) task of morphosyntactic disambiguation (Part
Of Speech Tagging)... / to syntactic parsing in information extraction and retrieval e.g.
2995.1 Intelligent Internet Systems - Levy, Weld (2000)(Correct)
this article. This work was funded by Oce of
Naval Research Grant N00014-98-1-0147, by National Science Foundation Grants IRI-9303461 and
IIS-9978567, by ARPA / Rome Labs grant F30602-95-1-0024, and b... / more ambitious than simple information extraction they seek to br automates the bulk of the wrapper-generation process with a combination
2770.2 Harvest: A Scalable, Customizable Discovery and Access System - Bowman (1995)(Correct)
Rapid growth in data volume, user base, and data diversity render Internet-accessible information
increasingly difficult to use effectively. In this paper we introduce Harvest, a system that
provides ... / the Essence customized information extraction system the Indie
2752.9 Regularized Principal Manifolds - Smola, Mika, Schölkopf, Williamson (1999)(Correct)
Many settings of unsupervised learning can be viewed as quantization problems --- the
minimization of the expected quantization error subject to some restrictions. This allows the use
of tools such ... / reflects our emphasis on information extraction by learning the coding
2653.7 PEA - a Personal Email Assistant with Evolutionary Adaptation - Winiwarter (1999)(Correct)
In this paper we present PEA, a Personal Email Assistant, which filters
incoming emails and ranks them according to their relevance. We provide
tools for the acquisition of individual user models, whi... / analysis Local documents Information extraction Templates Display of
2487.3 Satisfying Constraints on Extraction and Adjunction - Bouma, Malouf, Sag (1997)(Correct)
This paper is much improved thanks to our interactions with them. In addition, we thank Ann Copestake, Dan Flickinger, and Gertjan van Noord for helpful suggestions. Finally, this research was conduct... / might be sensitive to extraction information e.g. a phenomenon that
2468.0 I don't believe in word senses - Kilgarriff (1997)(Correct)
Word sense disambiguation assumes word senses. Within the lexicography and
linguistics literature, they are known to be very slippery entities. The paper looks at
problems with existing accounts of `w... / exercises in information extraction MUC- in
2403.7 Grammars Have Exceptions - Crescenzi, Mecca (1998)(Correct)
Extending database-like techniques to semi-structured and Web data sources is becoming
a prominent research field. These data sources are essentially collections of textual documents.
Hence, in this c... / Minerva a formalism for wrapper generation over semi-structured and
2396.3 Reasoning with inconsistency in structured text - Hunter (1999)(Correct)
Reasoning with inconsistency involves some compromise on classical logic. There is a range
of proposals for logics (called paraconsistent logics) for reasoning with inconsistency each with
pros and ... / and the output from information extraction systems in the form of
2339.9 Cut and Paste - Mecca, Atzeni (1998)(Correct)
The paper develops Editor, a language for manipulating semi-structured documents, such
as the ones typically available on the Web. Editor programs are based on two simple ideas,
taken from text editor... / project as a basis for a wrapper-generation toolkit. Introduction
2295.4 Tabling for Non-monotonic Programming - Swift (1999)(Correct)
this paper we describe tabling as it is implemented in the XSB system unknown Annals of Mathematics and Artificial Intelligence 0 (1999) ?--? 1
Tabling for Non-monotonic Programming
Terrance Swift
D... / psychiatric diagnosis information extraction from poorly structured
2268.0 Information Extraction: Beyond Document Retrieval - Gaizauskas, Wilks (1998)(Correct)
In this paper we give a synoptic view of the growth text processing technology
of information extraction (IE) whose function is to extract information about a
pre-specified set of entities, relations ... / Society of R.O.C. Information Extraction Beyond Document Retrieval
2205.7 Information Extraction from World Wide Web - A Survey - Eikvil (1999)(Correct)
This report will first, in Chapter 2, give an introduction to the field of information extraction and then, in Chapter 3, look at the development of the field of wrapper generation for Web sources. Ch... / Information Extraction from World Wide Web br Chapter Information Extraction Information extraction IE is
2078.9 Machine Learning for Information Extraction from Online Documents - Freitag (1996)(Correct)
The field of information extraction (IE) is concerned with applying
natural language processing (NLP) to extract essential details from text
documents automatically. Recent results have demonstrated t... / Machine Learning for Information Extraction from Online Documents
2067.7 BLT: Bi-Layer Tracing of HTTP and TCP/IP - Feldmann (2000)(Correct)
We describe BLT, a tool for extracting full HTTP level as well as TCP level traces via packet monitoring. This paper presents the software architecture that allows us to collect traces continuously, o... / is easier than layer information extraction because the switch is in
2065.4 A Conceptual Framework for Text Filtering - Oard, Marchionini (1996)(Correct)
This report develops a conceptual framework for text filtering practice and research,
and reviews present practice in the field. Text filtering is an information seeking process
in which documents are... / Stable and Structured Information Extraction Specific Unstructured
1991.3 Automating the Construction of Internet Portals with Machine Learning - McCallum, Nigam, Rennie, Seymore(Correct)
Internet portals are growing in popularity because they gather content from the Web and organize it for easy access, retrieval and search. For example, www.campsearch.com allows complex queries by a... / in reinforcement learning information extraction and text classification br search. . Information Extraction Information extraction is concerned
1983.4 A Computational Theory of Vocabulary Acquisition - Rapaport, Ehrlich (1998)(Correct)
As part of an interdisciplinary project to develop a computational cognitive model of a reader of narrative text, we are
developing a computational theory of how natural-language-understanding systems... / message-processing and information-extraction systems need to be robust
1981.0 The Indexing and Retrieval of Document Images: A Survey - Doermann (1998)(Correct)
The economic feasibility of maintaining large databases of document images has
created a tremendous demand for robust ways to access and manipulate the information
these images contain. In an attempt ... / image databases including information extraction and indexing and
1952.8 Word Sense Disambiguation And Its Application To Internet Search - Mihalcea (1999)(Correct)
ambiguation method presented here is
that it provides a ranking of possible associations between words senses, rather than a
binary yes/no decision for a possible sense combination. This proves to be ... / operators de ned for information extraction improve both the
1935.5 Improving Minority Class Prediction Using Case-Specific Feature.. - Cardie (1997)(Correct)
This paper addresses the problem of handling
skewed class distributions within the
case-based learning (CBL) framework. We
first present as a baseline an informationgain
-weighted CBL algorithm and ap... / and the acquisition of information extraction patterns i.e.concept br semantic class and concept extraction information for each of these content
1925.6 Logic Programs for Intelligent Web Search - Thomas (1999)(Correct)
We present a general framework for the information extraction from web pages
based on a special wrapper language, called token-templates. By using tokentemplates
in conjunction with logic programs we... / a general framework for the information extraction from web pages based on a br . N. Ashish and C. Knoblock. Wrapper generation for semistructured internet
1925.6 Intelligent Web Querying with Logic Programs - Bernd Thomas (1998)(Correct)
We present a general framework for the information extraction from web pages based
on a special wrapper language, called token-templates. By using token-templates in conjunction
with logic programs we... / a general framework for the information extraction from web pages based on a br N. Ashish and C. Knoblock. Wrapper generation for semistructured internet
1904.8 New Directions in Video Information Extraction and Summarization - Wactlar(Correct)
The Informedia Digital Video Library project provided a technological foundation for full content indexing and
retrieval of video and audio media. New directions for this research extend to: (1) searc... / New Directions in Video Information Extraction and Summarization Howard
1869.0 Can we make Information Extraction more adaptive? - Wilks, Catizone (1999)(Correct)
It seems widely agreed that IE (Information Extraction) is now a tested
language technology that has reached precision+recall values that put it
in about the same position as Information Retrieval a... / Can we make Information Extraction more adaptive Yorick
1790.7 Modeling of Moving Objects in a Video Database - Li, Özsu, Szafron (1997)(Correct)
Modeling moving objects has become a topic of increasing interest in the area of video databases.
Two key aspects of such modeling are spatial and temporal relationships. In this paper we introduce
an... / are used. The motion information extraction is then used at an
1787.6 Using default logic for lexical knowledge - Hunter (1997)(Correct)
Lexical knowledge is knowledge about the morphology, grammar,
and semantics of words. This knowledge is increasingly important
in language engineering, and more generally in information retrieval, i... / information filtering and information extraction. Perhaps the most
1688.7 IR and AI: traditions of representation and anti-representation in.. - Wilks(Correct)
The paper is concerned with the role of conceptual representations
in access to information, as for example, from the World Wide
Web. It contrasts two quite different traditions for doing this: In... / IR and more recently Information Extraction IE a development of
1665.8 XWRAP: An XML-enabled Wrapper Construction System for Web Information .. - Liu, Pu, Han (2000)(Correct)
The amount of useful semi-structured data on the web continues to grow at a stunning pace. Often
interesting web data are not in database systems but in HTML pages, XML pages, or text files.
Data in t... / developers as declarative information extraction rules. The second phase br the XML documents. The XWRAP wrapper generation framework has three distinct
1664.6 A Cognitive Bias Approach to Feature Selection and Weighting for.. - Cardie(Correct)
Research in psychology, psycholinguistics, and cognitive science has discovered and examined
numerous psychological constraints on human information processing. Short term memory
limitations, a focu... / be critical for the larger information extraction task within which the
1658.9 A Parallel System for Textual Inference - Harabagiu, Moldovan (1999)(Correct)
This paper presents a possible solution for the
text inference problem - extracting information unstated in
a text, but implied. Text inference is central to natural language
applications such as info... / applications such as information extraction and dissemination text
1647.3 Information Processing by a Perceptron in an Unsupervised Learning.. - Nadal (1993)(Correct)
We study the ability of a simple neural network (a perceptron architecture, no hidden units, binary outputs) to process information in the context of an unsupervised learning task. The network is aske... / Data analysis is a form of information extraction. To give an example for
1602.4 Building Domain-Specific Search Engines with Machine Learning.. - McCallum, Nigam, Rennie, Seymore (1999)(Correct)
Domain-specific search engines are becoming increasingly
popular because they offer increased accuracy
and extra features not possible with the
general, Web-wide search engines. For example,
www.camps... / text classification and information extraction that automates efficient br Information Extraction Information extraction is concerned
1601.1 Learning to Extract Keyphrases from Text - Turney (1999)(Correct)
Many academic journals ask their authors to provide a list of about five to fifteen key words,
to appear on the first page of each article. Since these key words are often phrases of two or
more words... / is also distinct from information extraction the task that has been
1600.5 Retrieval and Reasoning in Distributed Case Bases - Nagendra Prasad (1995)(Correct)
The proliferation of electronically available networked information has led researchers to
examine the issues involved in developing automated methods for gathering information in
response to a query ... / Much of the work in information extraction and text summarization
1576.6 Ontology-Based Extraction and Structuring of Information from.. - Embley, Campbell, Liddle, Smith (1998)(Correct)
We can extract and structure information from documents if we can match attributes
with document data values and associate these matched attribute-value pairs
as tuples in relations. In this paper we ... / data semistructured data information extraction information structuring br data information extraction information structuring ontology
1532.9 An Overview of Document Mining Technology - Dixon (1997)(Correct)
Living through the Information Revolution is becoming a difficult task - humans were not
designed to process massive quantities of information. The computer first found it's use in
speeding our number... / mining text mining information extraction information retrieval br text mining information extraction information retrieval data mining
1530.0 MILK: a Hybrid system for Multilingual Indexing and Information.. - Bolioli, Dini, Di Tomaso, Goy.. (1997)(Correct)
Substance
Countable
Countable Substance
Human Animal Inanimate
Figure 2: LKML hierarchy: top level.
tic typing and recursive typing (identifying larger
semantic tags) over a text is a "semi-structure... / Multilingual Indexing and Information Extraction A. Bolioli and L. br between information extraction and information retrieval in a web
1509.6 Designing Intelligent Interfaces For Users With Memory And Language.. - Singh (2000)(Correct)
The main contribution of this paper is to discuss in depth the issues related to the design of
computer interfaces for users with language limitations. Language limitations are found to
various degree... / information retrieval and information extraction databases and software
1507.3 Dynamic Information Filtering - Baudisch (2001)(Correct)
The goal of information filtering systems (IF systems) is to support users in finding relevant information from a dynamic base of data objects. IF systems base their relevance computations on so-calle... /
1483.0 Reasoning about Textual Similarity in a Web-Based Information Access.. - Cohen(Correct)
The degree to which information sources are pre-processed by Webbased
information systems varies greatly. In search engines like Altavista, little
pre-processing is done, while in "knowledge integra... / retrieval similarity information extraction . Introduction There br data is to partially automate wrapper generation Wrapper automation
1475.3 Semi-automatic Wrapper Generation for Internet Information Sources - Ashish (1997)(Correct)
To simplify the task of obtaining information from the
vast number of informationsources that are available on the
WorldWide Web (WWW),we are buildinginformationmediators
for extracting and integratin... / Wrapper induction for information extraction. In International Joint br Semi-automatic Wrapper Generation for Internet Information
1458.0 Image Fusion - Maître, Bloch (1997)(Correct)
We present the main lines along which information fusion has evolved from the
first days of data fusion up to image fusion, then we discuss some of the reasons why
image fusion cannot benefit from man... / are they combined . Information extraction from images It may
1452.9 LE PROJECT No 2110 - Extraction Of(Correct)
Description of a system for the automatic acquisition of
verbal case frames from corpora. The key target is to acquire
domain-specific relations rather than the standard relationships
found in general... / useful in lexically driven information extraction. As for information
1451.4 Information Extraction as a Stepping Stone toward Story Understanding - Riloff (1999)(Correct)
this article, we will refer to extraction patterns and case frames interchangeably, with
the understanding that case frames for other tasks may be significantly more complex. unknown In Understanding ... / from MIT Press. Information Extraction as a Stepping Stone toward br . What is information extraction Information extraction is a
1432.3 From IR to IE through GL - Bolioli, Dini, Di Tomaso, Sestero (1997)(Correct)
This paper describes the project MILK (Multilingual Indexing based on Lexical
Knowledge), a cooperation between University of Brandeis and CELI (Centro
per l'Elaborazione del Linguaggio e dell'Informa... / on the interaction between information extraction and information retrieval br between information extraction and information retrieval in a web
1426.2 Merging potentially inconsistent items of structured text - Hunter (2000)(Correct)
Structured text is a general concept that is implicit in a variety of approaches to handling
information. Syntactically, an item of structured text is a number of grammatically simple
phrases togeth... / and the output from information extraction systems in the form of
1408.0 Toward Team-Oriented Programming - Pynadath, Tambe, Chauvat, Cavedon (1999)(Correct)
The promise of agent-based systems is leading towards the development of
autonomous, heterogeneous agents, designed by a variety of research/industrial groups
and distributed over a variety of platf... / environments and information extraction on the Internet
1404.9 Information Retrieval: Still Butting Heads with Natural Language.. - Smeaton (1997)(Correct)
Information retrieval (IR) is about finding documents which
may be of relevance to a user's query, from within a corpus or collection
of texts. While apparently a simple task at first glance, IR is ... / on the whole IR task. Information extraction is also fundamentally br task. . Information Extraction Information extraction IE is a
1385.8 Constructing Biological Knowledge Bases by Extracting Information.. - Craven, Kumlien (1999)(Correct)
Recently, there has been much effort in making databases for molecular biology more accessible and interoperable. However, information in text form, such as MEDLINE records, remains a greatly underuti... / in learning such information-extraction routines. We also present br as one of information extraction. Information extraction IE involves
1384.9 From local to global coherence: A bottom-up approach to text planning - Marcu (1997)(Correct)
We present a new, data-driven approach to text planning,
which can be used not only to map full knowledge
pools into natural language texts, but also to generate
texts that satisfy multiple, high-leve... / by systems developed for information extraction tasks one can use the
1377.6 TextNet - A Text-Based Intelligent System - Harabagiu (1996)(Correct)
A large collection of texts may be reached through the Internet and this provides a powerful
platform from which common-sense knowledge may be gathered. This paper presents a system
that contains a co... / abductive inference information extraction on Internet coherence
1373.6 Text Categorization Through Probabilistic Learning: Applications to.. - Bennett (1998)(Correct)
Author: Paul N. Bennett
Title: Text Categorization Through Probabilistic Learning: Applications to Recommender Systems
Supervising Professor: Raymond J. Mooney, Ph.D.
With the growth of the World Wide... / . . Information Extraction . br . Information Extraction Information Extraction attempts to
1368.4 Using HTML Formatting to Aid in Natural Language Processing on the.. - DiPasquo (1998)(Correct)
Because of its magnitude and the fact that it is not computer understandable, the World
Wide Web has become a prime candidate for automatic natural language tasks. This thesis
argues that there is inf... / . Learning Rules for Information Extraction . . The Data Set br problems of information extraction and information retrieval over over a
1344.1 Distributed Knowledge Networks - Vasant Honavar (1998)(Correct)
Distributed Knowledge Networks (DKN)
provide some of the key enabling technologies for translating
recent advances in automated data acquisition,
digital storage, computers and communications into
fun... / for information retrieval information extraction assimilation and
1339.2 Extraction of Keyphrases from Text: Evaluation of Four Algorithms - Turney (1997)(Correct)
This report presents an empirical evaluation of four algorithms for automatically extracting
keywords and keyphrases from documents. The four algorithms are compared using five different
collections o... / work addresses the task of information extraction. An information
1333.3 A sequential model for attentive object selection - Fellenz (1994)(Correct)
A biologically motivated model for object selection is proposed which combines
strategies for preattentive segmentation and attentive object selection to extract consistent
descriptions of objects in ... / nonselective unidirectional information extraction There are some major
1323.5 Generating Finite-State Transducers For Semi-Structured Data.. - Hsu, Dung (1998)(Correct)
Integrating a large number of Web information sources may significantly increase the utility of the World-Wide Web. A promising solution to the integration is through the use of a Web Information medi... / Data Wrapper Induction Information Extraction World Wide Web. . br C.A. Knoblock. Semi-automatic wrapper generation for internet information
1311.2 Towards a Hybrid - Br Id (1997)(Correct)
Generation System
Maria ARETOULAKI
Dept. of Pattern Recognition (Informatik 5),
University of Erlangen-Nuremberg,
Martensstrasse 3, 91058 Erlangen, Germany.
Tel: +49 9131 857824
Fax: +49 9131 30381... / methodology is the DIDEROT information extraction system as presented in
1307.8 A Statistical Information Extraction System for Turkish - Tür (1999)(Correct)
Information Extraction (IE) is the process of analyzing natural language
text or speech, and collecting information about specified types
of entities, relationships, or events, such as marking perso... / A Statistical Information Extraction System for Turkish
1298.7 Learning Information Extraction Rules for Semi-structured and Free.. - Soderland (1999)(Correct)
A wealth of on-line text information can be made available to automatic processing
by information extraction (IE) systems. Each IE application needs a separate set of rules tuned to
the domain and w... / The Netherlands. Learning Information Extraction Rules for Semi-structured br N. and Knoblock C. Wrapper generation for semi-structured Internet
1293.4 Algebraic Video for Composition and Content-Based Access - Weiss, Duda, Gifford(Correct)
We introduce a new data model called algebraic
video that provides operations for the composition,
search, navigation and playback of digital video presentations.
Video presentations are composed usin... / feasible other forms of information extraction can be employed. Text
1257.7 Recent Advances in Motion Understanding - Beauchemin, Bajcsy, Barron(Correct)
Probably the most ambitious goal of Computer Vision is to build the universal vision machine,
capable of guiding itself through arbitrary environments, recognizing objects along its path and reachin... / agent the amount of information extraction from the spatiotemporal
1249.5 Extracting and Converting Data from Semistructured Biological.. - Coupaye, Etzold(Correct)
One fundamental property underlies most biological databanks:
their availability in text format. We propose an approach to retrieve and
convert biological data stored in textual flat files into inform... / The complete process of information extraction and conversion is referred br . Data Extraction Information or data extraction is
1237.4 Rich Schemata for Semistructured Data: Thesis proposal - Bergholz (1999)(Correct)
Semistructured data is one of the new challenging research areas in
the database community. We believe that the underlying problem is
that of moving from content-based to structure-based querying. For... / arises in the context of information extraction from the WWW. A main
1236.9 Memory-Based Shallow Parsing - Daelemans, Buchholz, Veenstra (1999)(Correct)
We present a memory-based learning (MBL) approach to shallow parsing in which POS tagging, chunking, and identification of syntactic relations are formulated as memory-based modules. The experiments r... / in applications such as information extraction and summary generation.
1236.6 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 ... / Of California San Diego Information Extraction Using Hidden Markov
1231.4 Automatic Digital Video Production Concepts - Ahanger, Little (1998)(Correct)
Video production involves conceiving a story, shooting raw video footage, and editing
the final piece. Editing involves manually cutting frames and frame sequences from the raw video
and composing the... / efficient. The process of information extraction and related issues are
1219.4 Using Machine Learning for Assigning Indices to Textual Cases - Brüninghaus, Ashley(Correct)
This paper reports preliminary work on developing methods automatically to index cases described in text so that
a case-based reasoning system can reason with them. The goal is to classify the text of... / in many fields within AI. Information Extraction IE Cowie Lehnert
1213.4 ILP: Just Do It - Page (2000)(Correct)
Inductive logic programming (ILP) is built on a foundation
laid by research in other areas of computational logic. But in spite of this
strong foundation, at 10 years of age ILP now faces a number... / information retrieval and information extraction. Arguably natural
1202.2 Information Extraction from the Web - May, Lausen (2000)(Correct)
The goal of information extraction from the Web is to provide an integrated view on data
from autonomous, heterogeneous information sources. The main problem with current wrapper
/mediator approache... / Information Extraction from the Web Wolfgang br automatical matching-based wrapper generation for data-rich and
1195.4 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... / Information extraction for semi-structured
1186.9 Adaptation To The User's Tasks - Höök (1995)(Correct)
Adapting explanations to users with varying background knowledge and
abilities is a difficult task: the explanation content, style, amount of details,
terms used, etc. may be affected in various ways.... / both with navigation and information extraction. Apart from the learning
1186.0 Morphological Cues for Lexical Semantics - Light (1996)(Correct)
Most natural language processing tasks require
lexical semantic information. Automated
acquisition of this information
would thus increase the robustness and
portability of NLP systems. This paper
des... / front end to a database information extraction machine translation and
1176.0 Template-based Information Extraction from Tree-structured HTML.. - Yih (1997)(Correct)
iii
List of Figures vii
List of Tables ix
Chapter 1 Introduction 1
1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
1.2 The Importance of Information Extraction on Agent Technol... / Template-based Information Extraction from Tree-structured HTML
1166.5 Using Decision Trees for Coreference Resolution - Mccarthy (1995)(Correct)
This paper describes resolve, a system that uses decision trees to learn how to classify coreferent phrases in the domain of business joint ventures. An experiment is presented in which the performanc... / The goal of an Information Extraction IE system is to
1155.3 A methodology for building information agents - Gao, Sterling (1998)(Correct)
Information agents are increasingly being used for efficient and precise information retrieval from
the Internet. Most of them are handcrafted from scratch and can not easily be adapted to other
searc... / different from traditional Information Extraction IE that works on natural br agents and semi-automatic wrapper generation Research has also
1147.3 Informedia - Search and Summarization in the Video Medium - Wactlar (2000)(Correct)
The Informedia system provides "full-content" search and retrieval of current and past TV and radio news
and documentary broadcasts. The system implements a fully automatic intelligent process to enab... / goals fully automated information extraction and full-content
1145.9 A Learning Approach to Shallow Parsing - Muñoz, Punyakanok, Roth, Zimak (1999)(Correct)
A SNoW based learning approach to shallow parsing tasks is presented and studied experimentally.
The shallow parsing method suggested learns to identify syntactic patterns by
combining simple predic... / applications including information extraction and text summarization