An Investigation Into Statistically-based Lexical Ambiguity Resolution PDF Download

Author: Stephen Sutton
Publisher:
ISBN:
Category :
Languages : en
Pages :

View

Book Description

Author: Steven L. Small
Publisher: Elsevier
ISBN: 0080510132
Category : Computers
Languages : en
Pages : 529

View

Book Description
The most frequently used words in English are highly ambiguous; for example, Webster's Ninth New Collegiate Dictionary lists 94 meanings for the word "run" as a verb alone. Yet people rarely notice this ambiguity. Solving this puzzle has commanded the efforts of cognitive scientists for many years. The solution most often identified is "context": we use the context of utterance to determine the proper meanings of words and sentences. The problem then becomes specifying the nature of context and how it interacts with the rest of an understanding system. The difficulty becomes especially apparent in the attempt to write a computer program to understand natural language. Lexical ambiguity resolution (LAR), then, is one of the central problems in natural language and computational semantics research. A collection of the best research on LAR available, this volume offers eighteen original papers by leading scientists. Part I, Computer Models, describes nine attempts to discover the processes necessary for disambiguation by implementing programs to do the job. Part II, Empirical Studies, goes into the laboratory setting to examine the nature of the human disambiguation mechanism and the structure of ambiguity itself. A primary goal of this volume is to propose a cognitive science perspective arising out of the conjunction of work and approaches from neuropsychology, psycholinguistics, and artificial intelligence--thereby encouraging a closer cooperation and collaboration among these fields. Lexical Ambiguity Resolution is a valuable and accessible source book for students and cognitive scientists in AI, psycholinguistics, neuropsychology, or theoretical linguistics.

Author: Science Society Cognitive, Con
Publisher: Psychology Press
ISBN: 9780805814873
Category : Psychology
Languages : en
Pages : 1080

View

Book Description
This volume features the complete text of all regular papers, posters, and summaries of symposia presented at the 15th annual meeting of the Cognitive Science Society.

Author: Paola Merlo
Publisher: John Benjamins Publishing
ISBN: 9027297487
Category : Language Arts & Disciplines
Languages : en
Pages : 373

View

Book Description
Lexical effects on language processing are currently a major focus of attention in studies of sentence comprehension. This thematic collection provides a uniquely multi-faceted and integrated viewpoint on key aspects of lexicalist theories, drawing from the fields of theoretical linguistics, computational linguistics, and psycholinguistics. The focus of this stimulating volume is on a number of central topics: The discussion of foundational issues concerning the nature of the lexicon and its relationship to sentence understanding; the exploration of the relationship between syntactic and lexical processing; and the investigation of the specific content of lexical entries, especially for verbs. The authors draw on a range of methodologies, from computational modeling to corpus studies to behavioral and neuro-imaging experimental techniques. The breadth of topics and methodologies is brought together by the articulated, critical analysis of the field provided in the introduction. The research reported here elaborates both the structure and the probabilistic content of lexical representations, and meets up with work in computer science, linguistics, psychology, and philosophy on the relation between conceptual, grammatical, and statistical knowledge.

Author: Albert Levi
Publisher: Springer
ISBN: 3540472436
Category : Computers
Languages : en
Pages : 1106

View

Book Description
This book constitutes the refereed proceedings of the 21st International Symposium on Computer and Information Sciences, ISCIS 2006, held in Istanbul, Turkey in October 2006. The 106 revised full papers presented together with five invited lectures were carefully reviewed and selected from 606 submissions.

Author: Alexander Franz
Publisher: Springer Science & Business Media
ISBN: 9783540620044
Category : Computers
Languages : en
Pages : 186

View

Book Description
This is an exciting time for Artificial Intelligence, and for Natural Language Processing in particular. Over the last five years or so, a newly revived spirit has gained prominence that promises to revitalize the whole field: the spirit of empiricism. This book introduces a new approach to the important NLP issue of automatic ambiguity resolution, based on statistical models of text. This approach is compared with previous work and proved to yield higher accuracy for natural language analysis. An effective implementation strategy is also described, which is directly useful for natural language analysis. The book is noteworthy for demonstrating a new empirical approach to NLP; it is essential reading for researchers in natural language processing or computational linguistics.

Author: Steven L. Small
Publisher:
ISBN:
Category : Ambiguity
Languages : en
Pages : 932

View

Book Description
The most frequently used words in English are highly ambiguous; for example, Webster's Ninth New Collegiate Dictionary lists 94 meanings for the word ""run"" as a verb alone. Yet people rarely notice this ambiguity. Solving this puzzle has commanded the efforts of cognitive scientists for many years. The solution most often identified is ""context"": we use the context of utterance to determine the proper meanings of words and sentences. The problem then becomes specifying the nature of context and how it interacts with the rest of an understanding system. The difficulty becomes espe.

Author: Louise A. Stanczak
Publisher:
ISBN:
Category :
Languages : en
Pages : 470

View

Book Description
Abstract: The use of two relevant sources of information--frequency and contextual plausibility--during on-line lexical and syntactic ambiguity resolution was examined as a function of verbal working memory capacity in four self-paced reading experiments. Experiment 1 demonstrated that lexical ambiguity resolution was more difficult when disambiguating sentences toward the less frequent homograph meaning. Experiment 2 showed that lexical ambiguity resolution was facilitated when homographs were preceded by strong contextual plausibility information. Experiment 3 found that syntactic ambiguity resolution was facilitated when verb bias information supported the syntactic parse, and experiment 4 demonstrated that contextual plausibility cues which disfavored the incorrect syntactic parse eased sentence comprehension. These results replicated previous research. Additionally, verbal working memory capacity did not mediate ambiguity effects in any of the four experiments. These data best support the working memory theory proposed by Caplan and Waters (1999), who hypothesize that on-line sentence comprehension is not mediated by verbal working memory resources, and these data provide evidence against other working memory theories that have been proposed by Just and Carpenter (1992) and Pearlmutter and MacDonald (1995). Ambiguity effects from each experiment were correlated with the other experiments. An individual's ability to use frequency information correlated with the ability to use contextual plausibility information within lexical ambiguities and within syntactic ambiguities. These results support a model of language in which frequency and contextual plausibility cues interact within each linguistic domain. An individual's ability to use homograph bias was not correlated with the ability to use verb bias, and an individual's ability to use contextual plausibility information was not correlated across lexical and syntactic ambiguities. These results support the autonomy theory, which posits that lexical and syntactic ambiguities are processed independently. These results are also discussed with respect to implications for the lexically-based constraint satisfaction theory, which hypothesizes that lexical and syntactic ambiguities are processed through a single mechanism by the same resources.

Author: Hinrich Schütze
Publisher: Center for the Study of Language and Information Publications
ISBN: 9781575860749
Category : Language Arts & Disciplines
Languages : en
Pages : 230

View

Book Description
This volume is concerned with how ambiguity and ambiguity resolution are learned, that is, with the acquisition of the different representations of ambiguous linguistic forms and the knowledge necessary for selecting among them in context. Schütze concentrates on how the acquisition of ambiguity is possible in principle and demonstrates that particular types of algorithms and learning architectures (such as unsupervised clustering and neural networks) can succeed at the task. Three types of lexical ambiguity are treated: ambiguity in syntactic categorisation, semantic categorisation, and verbal subcategorisation. The volume presents three different models of ambiguity acquisition: Tag Space, Word Space, and Subcat Learner, and addresses the importance of ambiguity in linguistic representation and its relevance for linguistic innateness.

Author: Vincent Ooi (B. Y.)
Publisher:
ISBN:
Category : Computers
Languages : en
Pages : 266

View

Book Description
This book introduces the reader to the changing notions of the lexicon and dictionary-making, using a convergence of perspectives from computational linguistics, corpus linguistics, and computational lexicography/lexicology. The main issues include: the relation between lexicon and corpus; corpus-based lexical modelling of language; the computational storage of the lexicon. From this, the book constructs and applies a framework for lexicon-building to a case study. It also stresses the importance of the Internet and World Wide Web for dictionary research and study.