Results 11 - 20
of
387
Unification-based Multimodal Parsing
- In COLING/ACL
, 1998
"... In order to realize their full potential, multimodal systems need to support not just input from multiple modes, but also synchronized integration of modes. Johnston et al (1997) model this integration using a unification operation over typed feature structures. This is an effective solution for a b ..."
Abstract
-
Cited by 84 (4 self)
- Add to MetaCart
In order to realize their full potential, multimodal systems need to support not just input from multiple modes, but also synchronized integration of modes. Johnston et al (1997) model this integration using a unification operation over typed feature structures. This is an effective solution for a broad class of systems, but limits multimodal utterances to combinations of a single spoken phrase with a single gesture. We show how the unification-based approach can be scaled up to provide a full multimodal grammar formalism. In conjunction with a multidimensional chart parser, this approach supports integration of multiple elements distributed across the spatial, temporal, and acoustic dimensions of multimodal interaction. Integration strategies are stated in a high level unification-based rule formalism supporting rapid prototyping and iterative development of multimodal systems. 1 Introduction Multimodal interfaces enable more natural and efficient interaction between humans and mach...
Feature Forest Models for Probabilistic HPSG Parsing
- In Computational Linguistics
, 2008
"... Probabilistic modeling of lexicalized grammars is difficult because these grammars exploit complicated data structures, such as typed feature structures. This prevents us from applying common methods of probabilistic modeling in which a complete structure is divided into substructures under the assu ..."
Abstract
-
Cited by 78 (11 self)
- Add to MetaCart
(Show Context)
Probabilistic modeling of lexicalized grammars is difficult because these grammars exploit complicated data structures, such as typed feature structures. This prevents us from applying common methods of probabilistic modeling in which a complete structure is divided into substructures under the assumption of statistical independence among sub-structures. For example, part-of-speech tagging of a sentence is decomposed into tagging of each word, and CFGparsing is split into applications of CFGrules. These methods have relied on the structure of the target problem, namely lattices or trees, and cannot be applied to graph structures including typed feature structures. This article proposes the feature forest model as a solution to the problem of probabilistic modeling of complex data structures including typed feature structures. The feature forest model provides a method for probabilistic modeling without the independence assumption when probabilistic events are represented with feature forests. Feature forests are generic data structures that represent ambiguous trees in a packed forest structure. Feature forest models are maximum entropy models defined over feature forests. A dynamic programming algorithm is proposed for maximum entropy estimation without unpacking feature forests. Thus probabilistic modeling of
TDL -- A Type Description Language for Constraint-Based Grammars
, 1994
"... This paper presents TDL, a typed feature-based rein'cscnt, al,ion language and inference sysl.cnt. Type dclini l,ions in TDL consis[ of (.ypc and feature coustraints over (,he booltan cmmc(:ives. TDL supt)ors opera and closed-- wm4d reasoning over types and allows for l)arl. iLions and im:ompa( ..."
Abstract
-
Cited by 69 (20 self)
- Add to MetaCart
This paper presents TDL, a typed feature-based rein'cscnt, al,ion language and inference sysl.cnt. Type dclini l,ions in TDL consis[ of (.ypc and feature coustraints over (,he booltan cmmc(:ives. TDL supt)ors opera and closed-- wm4d reasoning over types and allows for l)arl. iLions and im:ompa(,iblc tyt)cs. Working with partially as wcll as with ILlly expanded types is possible. Efii(:it:nt reasoning ht TD is accomplished Lhrougi Sl)ccializcd modules. Topical Paper. pic Arch: sofi,war, fin' NIA', grammar formalism for typed feature structures.
Finite-state multimodal parsing and understanding
- In Proceedings of COLING 2000
, 2000
"... Multimodal interfaces require effective parsing and understanding of utterances whose content is distributed across multiple input modes. Johnston 1998 presents an approach in which strategies for multimodal integration are stated declaratively using a unification-based grammar that is used by a mul ..."
Abstract
-
Cited by 62 (14 self)
- Add to MetaCart
(Show Context)
Multimodal interfaces require effective parsing and understanding of utterances whose content is distributed across multiple input modes. Johnston 1998 presents an approach in which strategies for multimodal integration are stated declaratively using a unification-based grammar that is used by a multidimensional chart parser to compose inputs. This approach is highly expressive and supports a broad class of interfaces, but offers only limited potential for mutual compensation among the input modes, is subject to significant concerns in terms of computational complexity, and complicates selection among alternative multimodal interpretations of the input. In this paper, we present an alternative approach in which multimodal parsing and understanding are achieved using a weighted finite-state device which takes speech and gesture streams as inputs and outputs their joint interpretation. This approach is significantly more efficient, enables tight-coupling of multimodal understanding with speech recognition, and provides a general probabilistic framework for multimodal ambiguity resolution. 1
Multimodal Integration - A Statistical View
- IEEE Transactions on Multimedia
, 1999
"... This paper presents a statistical approach to developing multimodal recognition systems and, in particular, to integrating the posterior probabilities of parallel input signals involved in the multimodal system. We first identify the primary factors that influence multimodal recognition performance ..."
Abstract
-
Cited by 60 (11 self)
- Add to MetaCart
(Show Context)
This paper presents a statistical approach to developing multimodal recognition systems and, in particular, to integrating the posterior probabilities of parallel input signals involved in the multimodal system. We first identify the primary factors that influence multimodal recognition performance by evaluating the multimodal recognition probabilities. We then develop two techniques, an estimate approach and a learning approach, which are designed to optimize accurate recognition during the multimodal integration process. We evaluate these methods using Quickset, a speech/gesture multimodal system, and report evaluation results based on an empirical corpus collected with Quickset. From an architectural perspective, the integration technique presented here offers enhanced robustness. It also is premised on more realistic assumptions than previous multimodal systems using semantic fusion. From a methodological standpoint, the evaluation techniques that we describe provide a valuable too...
Probabilistic Syntax
, 2002
"... istic methods for syntax, just as for a long time McCarthy and Hayes (1969) discouraged exploration of probabilistic methods in Artificial Intelligence. Among his arguments were that: (i) Probabilistic models wrongly mix in world knowledge (New York occurs more in text than Dayton, Ohio, but for no ..."
Abstract
-
Cited by 55 (2 self)
- Add to MetaCart
istic methods for syntax, just as for a long time McCarthy and Hayes (1969) discouraged exploration of probabilistic methods in Artificial Intelligence. Among his arguments were that: (i) Probabilistic models wrongly mix in world knowledge (New York occurs more in text than Dayton, Ohio, but for no linguistic reason), (ii) Probabilistic models don't model grammaticality (neither Colorless green ideas sleep furiously nor Furiously sleep ideas green colorless have previously been uttered -- and hence must be estimated to have probability zero, Chomsky wrongly assumes -- but the former is grammatical while the latter is not, and (iii) Use of probabilities does not meet the goal of describing the mind-internal I-language as opposed to the observed-in-the-world E-language. This chapter is not meant to be a detailed critique of Chomsky's arguments -- Abney (1996) provides a survey and a rebuttal, and Pereira (2000) has further useful discussion -- but some of these concerns are still importa
Multilingual lexical representation’
, 1992
"... Abstract The approach to multilingual lexical representation developed as part of the AC-QUILEX Lexical Knowledge Base (LKB) discussed with specific reference to complex translation equivalence. The treatment described provides a lexicalist account of translation mismatches in terms of translation ..."
Abstract
-
Cited by 51 (12 self)
- Add to MetaCart
Abstract The approach to multilingual lexical representation developed as part of the AC-QUILEX Lexical Knowledge Base (LKB) discussed with specific reference to complex translation equivalence. The treatment described provides a lexicalist account of translation mismatches in terms of translation links which capture cross-linguistic generalizations across sets of semantically related lexical items, and can be readily integrated with several transfer-based MT systems.
Default Representation in Constraint-Based Frameworks
- Computational Linguistics
, 1998
"... this paper allows any defaults to be overridden by defaults which are associated with more specific types: thus priority ordering reflects the type hierarchy ordering. (In 6.2, we will mention other possibilities for imposing a priority order on defaults.) Barring criterion 6, all of the above ..."
Abstract
-
Cited by 49 (6 self)
- Add to MetaCart
this paper allows any defaults to be overridden by defaults which are associated with more specific types: thus priority ordering reflects the type hierarchy ordering. (In 6.2, we will mention other possibilities for imposing a priority order on defaults.) Barring criterion 6, all of the above properties are necessary for making default unification behave as much like normal unification as possible, save that (default) information can be overridden. These criteria ensure that the default unification operation has properties familiar from monotonic unification, such as determinacy, the way information is accumulated, the conditions when unification fails, and order independence. Since this guarantees that default unification shares many of the properties of normal unification, a `seamless transition' is possible between the monotonic approach to linguistic analysis supplied by normal unification, and the extension to these analyses provided by supplying default constraints and default unification operating over them. We will justify these assumptions with respect to particular linguistic examples in 4
Electronic contracting with cosmos - how to establish, negotiate and execute electronic contracts on the internet
- Electronic Contracts on the Internet. 2 nd Int. Enterprise Distributed Object Computing Workshop (EDOC '98
, 1998
"... Today, the Internet gains more and more attraction even for small companies to contact business partners and to automate cooperation between each other. However, the smaller the company the higher the relative setup costs that are required if the complete process of a commercial transaction is to be ..."
Abstract
-
Cited by 49 (2 self)
- Add to MetaCart
(Show Context)
Today, the Internet gains more and more attraction even for small companies to contact business partners and to automate cooperation between each other. However, the smaller the company the higher the relative setup costs that are required if the complete process of a commercial transaction is to be supported. We propose COSMOS as an Internet-based electronic contracting service that facilitates commercial partners with offer catalogues, a brokerage service, contract negotiation and signing as well as contract execution. The COSMOS architecture supports these functions in an integrated, unified way. The design and execution of contracts integrates patterns from the CORBA Joint Business Object Facility.
