Improving subcategorization acquisition using word sense disambiguation
Published 1 January 2003Open access
Anna Korhonen, Judita Preiss
Citations23
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
An evaluation of the enriched subcategorization acquisition system using 29 'difficult' English verbs shows that WSD helps to improve the acquisition performance.
Abstract
We investigate the change in performance of automatic subcategorization acquisition when a word sense disambiguation (WSD) system is employed to guide the acquisition process. As a subgoal, this involves creating a probabilistic WSD system, which we evaluate on the Senseval-2 English allwords task data. We carry out an evaluation of the enriched subcategorization acquisition system using 29 `dif- cult' English verbs which shows that WSD helps to improve the acquisition performance.
Keywords
Computer Science
Foundations of statistical natural language processing
9,996 Citations1999Christopher D. Manning, Hinrich Schütze
International Journal of LexicographyIntroduction to WordNet: An On-line Lexical Database<sup>*</sup>
4,207 Citations1990George A. Miller, Richard Beckwith +3 more
Standard alphabetical procedures for organizing lexical information put together words that are spelled alike and scatter words with similar or related meanings haphazardly through the list.
ArXiv.orgAn Empirical Study of Smoothing Techniques for Language Modeling
633 Citations1996Stanley F. Chen, Joshua Goodman
Automatic extraction of subcategorization from corpora
267 Citations1997Ted Briscoe, John M. Carroll
A novel technique and implemented system for constructing a subcategorization dictionary from textual corpora achieves accuracy comparable to previous approaches, which are all limited to a highly restricted set of subc categorization classes.
Robust Accurate Statistical Annotation of General Text
248 Citations2002Ted Briscoe, John A. Carroll
A robust accurate domain-independent approach to statistical parsing incorporated into the new release of the ANLT toolkit, and publicly available as a research tool.
Comlex Syntax
205 Citations1994Ralph Grishman, Catherine Macleod +1 more
The design of Comlex Syntax is described, a computational lexicon providing detailed syntactic information for approximately 38,000 English headwords, and the types of errors which arise in creating such a lexicon are considered.
Seoul National University Open Repository (Seoul National University)100 Million Words of English:The British National Corpus (BNC)
198 Citations1992Geoffrey Leech
100 Million Words of English: The British National Corpus (BNC) is a celebration of 100 million words of English.
Computational LinguisticsThe Interaction of Knowledge Sources in Word Sense Disambiguation
166 Citations2001Mark Stevenson, Yorick Wilks
This work presents a sense tagger which uses several knowledge sources and attempts to disambiguate all content words in running text rather than limiting itself to treating a restricted vocabulary of words.
Does Baum-Welch re-estimation help taggers?
129 Citations1994David Elworthy
Two experiments designed to determine how much manual training information is needed for speech tagging by Hidden Markov Model suggest that initial biasing of either lexical or transition probabilities is essential to achieve a good accuracy and reveal three distinct patterns of Baum-Welch reestimation.
English Tasks: All-Words and Verb Lexical Sample
124 Citations2001Martha Palmer, Christiane Fellbaum +3 more
The experience in preparing the lexicon and sense-tagged corpora used in the English all-words and lexical sample tasks of Senseval-2 is described.
University of North Texas Digital Library (University of North Texas)An automatic method for generating sense tagged corpora
106 Citations1999Rada Mihalcea, Dan Moldovan
A novel approach to automatically generate arbitrarily large corpora for word senses based on information provided in WordNet, used to formulate queries consisting of synonyms or definitions of word senses, and information gathered from Internet using existing search engines is presented.
Computers and the HumanitiesHierarchical Decision Lists for Word Sense Disambiguation
97 Citations2000David Yarowsky
A supervised algorithm for word sensedambiguation based on hierarchies of decision lists thatorts a useful degree of conditional branching while minimizing the training data fragmentation typical of decision trees.
Automatic extraction of subcategorization frames for Czech
68 Citations2000Anoop Sarkar, Daniel Zeman
It is shown how the learning algorithm can be used to discover previously unknown subcategorization frames from the Czech Prague Dependency Treebank and used to label dependents of a verb in the Czech treebank as either arguments or adjuncts.
Large lexicons for natural language processing: utilising the grammar coding system of LDOCE
67 Citations1987B. K. Boguraev, Ted Briscoe
The development of a dictionary support environment linking a restructured version of the Longman Dictionary of Contemporary English to natural language processing systems is described and an evaluation of the utility of the grammar coding system for use by automatic natural language parsing systems is offered.
Natural Language EngineeringWord sense disambiguation with pattern learning and automatic feature selection
47 Citations2002Rada Mihalcea
The ideas described in this paper were implemented in a system that achieves excellent performance on the data provided during the SENSEVAL-2 evaluation exercise, for both English all words and English lexical sample tasks.
arXiv (Cornell University)Machine Learning with Lexical Features: The Duluth Approach to Senseval-2
26 Citations2002Ted Pedersen
Verb subcategorization frequency differences between business-news and balanced corpora
24 Citations2000Douglas Roland, Daniel Jurafsky +4 more
It is shown that all or nearly all of these shifts in subcategorization are realised via (often subtle) word sense differences, and suggests that stable cross corpus subc categorization frequencies may be found when verb sense is adequately controlled.
On the robustness of entropy-based similarity measures in evaluation of subcategorization acquisition systems
14 Citations2002Anna Korhonen, Yuval Krymolowski
The authors' experiments with two subcategorization acquisition systems show that similarity measures vary in their robustness, and while some are led astray by noise from smoothing, others are more resilient.
Subcategorization Acquisition as an Evaluation Method for WSD
8 Citations2002Judita Preiss, Anna Korhonen +1 more
The enhanced subcategorization acquisition system can be used as a task-based evaluation method for WSD systems where both the notion of sense and the sense’s relevance to the evaluation process is determined by the application itself.
Improving subcategorization acquisition with WSD
5 Citations2002Judita Preiss, Anna Korhonen
A small scale experiment with manually sense annotated data shows that accurate WSD indeed does improve the accuracy of the acquired subcategorization frames (SCFs).