Recent Advances in Natural Language Processing III

Selected papers from RANLP 2003

Editors
| IBM T.J. Watson Research Center
| University of Sheffield
| Bulgarian Academy of Sciences
| University of Wolverhampton
HardboundAvailable
ISBN 9789027247742 (Eur) | EUR 110.00
ISBN 9781588116185 (USA) | USD 165.00
 
e-Book
ISBN 9789027294685 | EUR 110.00 | USD 165.00
 
This volume brings together revised versions of a selection of papers presented at the 2003 International Conference on “Recent Advances in Natural Language Processing”. A wide range of topics is covered in the volume: semantics, dialogue, summarization, anaphora resolution, shallow parsing, morphology, part-of-speech tagging, named entity, question answering, word sense disambiguation, information extraction. Various ‘state-of-the-art’ techniques are explored: finite state processing, machine learning (support vector machines, maximum entropy, decision trees, memory-based learning, inductive logic programming, transformation-based learning, perceptions), latent semantic analysis, constraint programming. The papers address different languages (Arabic, English, German, Slavic languages) and use different linguistic frameworks (HPSG, LFG, constraint-based DCG).

This book will be of interest to those who work in computational linguistics, corpus linguistics, human language technology, translation studies, cognitive science, psycholinguistics, artificial intelligence, and informatics.
[Current Issues in Linguistic Theory, 260]  2004.  xii, 402 pp.
Publishing status: Available
Table of Contents
Editors’ Foreword
ix
I. Invited lectures
A type-theoretic approach to anaphora and ellipsis resolution
Chris Fox and Shalom Lappin
1
Human dialogue modelling using machine learning
Yorick Wilks, Nick Webb, Andrea Setzer, Mark Hepple and Roberta Catizone
17
Learning domain theories
Stephen G. Pulman and Maria Liakata
29
Recent developments in temporal information extraction
Inderjeet Mani
45
Annotation-based finite state processing in a large-scale NLP arhitecture
Branimir K. Boguraev
61
II. Lexical semantics and lexical knowledge acquisition
Acquiring lexical paraphrases from a single corpus
Oren Glickman and Ido Dagan
81
Multi-word collocation extraction by syntactic composition of collocation bigrams
Violeta Seretan, Luka Nerima and Eric Wehrli
91
Combining independent modules in lexical multiple-choice problems
Peter D. Turney, Michael L. Littman, Jeffrey Bigham and Victor Shnayder
101
Roget’s thesaurus and semantic similarity
Mario Jarmasz and Stan Szpakowicz
111
Clustering WordNet word senses
Eneko Agirre and Oier Lopez de Lacalle
121
Inducing hyperlinking rules in text collections
Roberto Basili, Maria Teresa Pazienza and Fabio Massimo Zanzotto
131
Near-synonym choice in natural language generation
Diana Zaiu Inkpen and Graeme Hirst
141
III. Tagging, parsing and syntax
Fast and accurate part-of-speech tagging: The SVM approach revisited
Jesús Giménez and Lluís Màrquez
153
Part-of-speech tagging with minimal lexicalization
Virginia Savova and Leon Peshkin
163
Accurate annotation: An efficiency metric
António Branco and João Silva
173
Structured parameter estimation for LFG-DOP
Mary Hearne and Khalil Sima’an
183
Parsing without grammar — Using complete trees instead
Sandra Kübler
193
Phrase recognition by filtering and ranking with perceptrons
Xavier Carreras and Lluís Màrquez
205
Cascaded finite-state partial parsing: A larger-first approach
Sebastian van Delden and Fernando Gomez
217
A constraint-based bottom-up counterpart to definite clause grammars
Henning Christiansen
227
IV. Information extraction
Using parallel texts to improve recall in botany
Mary McGee Wood, Susannah J. Lydon, Valentin Tablan, Diana Maynard and Hamish Cunningham
237
Marking atomic events in sets of related texts
Elena Filatova and Vasileios Hatzivassiloglou
247
Semantically driven approach for scenario recognition in the IE system FRET
Svetla Boytcheva, Milena Yankova and Albena Strupchanska
257
A framework for named entity recognition in the open domain
Richard J. Evans
267
V. TEXT SUMMARISATION AND DOCUMENT PROCESSING
Latent semantic analysis and the construction of coherent extracts
Tristan Miller
277
Facilitating email thread access by extractive summary generation
Ani Nenkova and Amit Bagga
287
Towards deeper understanding of the latent semantic analysis performance
Preslav Nakov, Elena Valchanova and Galia Angelova
297
Automatic linking of similar texts across languages
Bruno Pouliquen, Ralf Steinberger and Camelia Ignat
307
VI. OTHER NLP TOPICS
Verb phrase ellipsis detection using machine learning techniques
Leif Arda Nielsen
317
HPSG-based annotation scheme for corpora development and parsing evaluation
Kiril Iv. Simov
327
Arabic Morpho-syntax for Text-to-Speech
Allan Ramsay and Hanady Mansour
337
Guessing morphological classes of unknown German nouns
Preslav Nakov, Yury Bonev, Galia Angelova, Evelyn Gius and Walther von Hahn
347
Building sense tagged corpora with volunteer contributions over the Web
Rada Mihalcea and Timothy Chklovski
357
Reducing false positives by expert combination in automatic keyword indexing
Anette Hulth
367
Socrates: A question answering prototype for Bulgarian
Hristo T. Tanev
377
Unsupervised natural language disambiguation using non-ambiguous words
Rada Mihalcea
387
List of Contributors
397
Index
399
Subjects
BIC Subject: CF – Linguistics
BISAC Subject: LAN009000 – LANGUAGE ARTS & DISCIPLINES / Linguistics / General
U.S. Library of Congress Control Number:  2004062362