Corpus Processing for Lexical Acquisition

by Boguraev, Bran; Pustejovsky, James

• ISBN13: 9780262023924
• ISBN10: 026202392X
• Format: Hardcover
• Copyright: 1996-06-01
• Publisher: Bradford Books

Summary

The lexicon has emerged from the study of computational linguistics as a fundamental resource that enables a variety of linguistic processes to operate in the course of tasks ranging from language analysis and text processing to machine translation. Lexicon acquisition, therefore, plays an essential part in getting any natural language processing system to function in the real world. Computers that process natural language require a variety of lexical information in addition to what can be found in standard dictionaries. Moreover, machine-readable dictionaries of the conventional sort have been found to be inadequate for fully supporting realistic natural language processing tasks. This volume describes corpus processing techniques that can be used to extract the additional lexical information required. Bringing together a balanced blend of the theoretical and practical, the contributions provide the most recent look at lexical acquisition techniques and practices. These include coping with unknown lexicalizations, task-driven lexical induction, categorization of lexical units, lexical semantics from corpus analysis, and measuring lexical acquisition. The problems addressed reflect a host of topics including recognition of open compounds, incremental acquisition of meanings from sentence usages, recognition of new senses of existing words, sense disambiguation, recognition of specific classes of works, and recognition and annotation of patterns of word use, each of them important to the overall language analysis process, and each employing text analysis techniques in a useful and theoretically motivated way. Language, Speech, and Communication series

Table of Contents

Contributors	xiii
Preface	xv
Acknowledgments	xvii
I INTRODUCTION
Issues in Text-based Lexicon Acquisition	3	(18)
Branimir Boguraev
James Pustejovsky
The Problem of Lexical Knowledge Acquisition	4	(10)
Text-based Lexicon Acquisition	14	(7)
II COPING WITH UNKNOWN LEXICALIZATIONS
Internal and External Evidence in the Identification and Semantic Categorization of Proper Names	21	(20)
David D. McDonald
Introduction	21	(1)
Internal versus External Evidence	22	(2)
Procedure Overview: Delimit, Classify, Record	24	(6)
The Setting for the Process	30	(3)
Walking through an Example	33	(4)
Conclusions	37	(4)
Identifying Unknown Proper Names in Newswire Text	41	(20)
Inderjeet Mani
T. Richard MacMillan
Introduction	41	(1)
Approaches to Name Identification	41	(4)
Proper Names---Syntax and Semantics	45	(1)
Overall Algorithm	46	(2)
Mention Generator	48	(1)
Knowledge Sources	48	(2)
Representation of Uncertainty	50	(1)
Appositives	50	(1)
Conference	51	(6)
Evaluation	57	(1)
Conclusion	58	(3)
Categorizing and Standardizing Proper Nouns for Efficient Information Retrieval	61	(16)
Woojin Paik
Elizabeth D. Liddy
Edmund Yu
Mary McKenna
Introduction	61	(1)
Proper Noun Boundary Identification	61	(1)
Proper Noun Classification Scheme	62	(5)
Use of Proper Nouns in Matching	67	(1)
Performance Evaluation	68	(4)
System Comparisons	72	(1)
Future Directions	73	(4)
III TASK-DRIVEN LEXICON INDUCTION
Customizing a Lexicon to Better Suit a Computational Task	77	(20)
Marti A. Hearst
Hinrich Schutze
Introduction	77	(2)
Creating Categories from WordNet	79	(3)
A Topic Labeler	82	(2)
Augmenting Categories with Relevant Terms	84	(5)
Combining Distant Categories	89	(5)
Conclusions	94	(3)
Towards Building Contextual Representations of Word Senses Using Statistical Models	97	(20)
Claudia Leacock
Geoffrey Towell
Ellen M. Voorhees
Contextual Representations	97	(1)
Acquiring Topical Context	97	(10)
An Upper Bound for Classifier Performance	107	(2)
Acquiring Local Context	109	(4)
Conclusion	113	(4)
IV CATEGORIZATION OF LEXICAL UNITS
A Context Driven Conceptual Clustering Method for Verb Classification	117	(26)
Roberto Basili
Maria-Teresa Pazienza
Paola Velardi
Introduction	117	(8)
CIAULA: An Algorithm to Acquire Word Clusters	125	(10)
Basic Level Categories	135	(5)
Summary	140	(3)
Distinguished Usage	143	(32)
Scott A. Waterman
Introduction	143	(3)
Information Extraction	146	(1)
Functionality in Lexical Semantics	147	(4)
Integrating Syntactic with Semantic Constraints	151	(1)
Patterns	152	(3)
The Current State of Pattern Acquisition	155	(1)
Structural Similarity Clustering	156	(6)
Lexical Clustering Using Edit Distance	162	(3)
Context Clustering	165	(2)
Context Method Results	167	(4)
Conclusion	171	(4)
V LEXICAL SEMANTICS FROM CORPUS ANALYSIS
Detecting Dependencies between Semantic Verb Subclasses and Subcategorization Frames in Text Corpora	175	(16)
Victor Poznanski
Antonio Sanfilippo
Introduction	175	(1)
Background	176	(2)
Semantic Acquisition Programs	178	(8)
Using CorPSE: Trends and Limitations	186	(4)
Conclusions	190	(1)
Acquiring Predicate-Argument Mapping Information from Multilingual Texts	191	(14)
Chinatsu Aone
Douglas McKee
Introduction	191	(1)
Predicate-Argument Mapping Representation	191	(5)
Automatic Acquisition from Corpora	196	(4)
Conclusion	200	(5)
VI MEASURING LEXICAL ACQUISITION
Evaluation Techniques for Automatic Semantic Extraction: Comparing Syntactic and Window Based Approaches	205	(12)
Gregory Grefenstette
Introduction	205	(1)
Gold Standards Evaluation	206	(3)
Corpus	209	(1)
Semantic Extraction Techniques	210	(2)
Results	212	(3)
Conclusion	215	(2)
Bibliography	217	(12)
Author Index	229	(4)
Subject Index	233