Role of Word Sense Disalnbiguation in Lexical Acquisition: Predicting Semantics from Syntactic Cues

@inproceedings{Dorr1996RoleOW,
  title={Role of Word Sense Disalnbiguation in Lexical Acquisition: Predicting Semantics from Syntactic Cues},
  author={B. Dorr and Douglas A. Jones},
  booktitle={COLING},
  year={1996}
}
This paper addresses the issue of word-sense ambiguity in extraction from machine-readable resources for the construction of large-scale knowledge sources. We describe two experiments: one which ignored word-sense distinctions, resulting in 6.3% accuracy for semantic classification of verbs based on (Levin, 1993); and one which exploited word-sense distinctions, resulting in 97.9% accuracy. These experiments were dual purpose: (1) to validate the central thesis of the work of (Levin, 1993), i.e… Expand
Acquisition of Semantic Lexicons: Using Word Sense Disambiguation to Improve Precision
TLDR
This paper describes semantic filters designed to reduce the number of incorrect assignments made by a purely syntactic technique and demonstrates that it is possible to use these filters to build broad-coverage lexicons with minimal effort, at a depth of knowledge that lies at the syntax-semantics interface. Expand
Distinguishing systems and distinguishing senses: new evaluation methods for Word Sense Disambiguation
TLDR
A new in-depth empirical study of translingually-based sense inventories and distance measures, using statistics collected from native-speaker annotations of 222 polysemous contexts across 12 languages, shows that monolingual sense distinctions at most levels of granularity can be effectively captured by translations into some set of second languages. Expand
Automatic Verb Classification Based on Statistical Distributions of Argument Structure
TLDR
This work reports on supervised learning experiments to automatically classify three major types of English verbs, based on their argument structure-specifically, the thematic roles they assign to participants, using linguistically-motivated statistical indicators extracted from large annotated corpora to train the classifier. Expand
Understanding the role of conceptual relations in Word Sense Disambiguation
TLDR
It is concluded that conceptual relations provide a source of information that is insufficient by itself to achieve good disambiguation results, but can, however, be a very accurate heuristic in a combined system. Expand
Towards a Representation of Verbal Semantics – An Approach Based on Near-Synonyms
TLDR
This paper proposes using the distributional differences in the syntactic patterns of near-synonyms to deduce the relevant components of verb meaning, and aims to tease out the lexical semantic features as the explanation, and as the motivation of the Syntactic contrasts. Expand
Automatic acquisition of semantic classes for adjectives
EnglishThis thesis concerns the automatic acquisition of semantic classes for adjectives. Our work builds on two hypotheses: first, that some aspects of the semantics of adjectives are not totallyExpand
Applying Multi-Sense Embeddings for German Verbs to Determine Semantic Relatedness and to Detect Non-Literal Language
TLDR
This paper compares and extends multi-sense embeddings, in order to model and utilise word senses on the token level, and evaluates the model variants on various semantic tasks: semantic classification; predicting compositionality; and detecting non-literal language usage. Expand
Semantic Annotation of Verb Arguments in Shallow Parsed Polish Sentences by Means of the EM Selection Algorithm
  • E. Hajnicz
  • Computer Science
  • Aspects of Natural Language Processing
  • 2009
TLDR
This work adapts EM selection algorithm elaborated for extraction of syntactic valence frames for Word Sense Disambiguation (WSD) task, which requires a treebank with all nouns semantically annotated with such categories. Expand
Sense Tagging
Disambiguation Yorick Wilks and Mark Stevenson Department of Computer Science, University of She eld, Regent Court, 211 Portobello Street, She eld S1 4DP, UK fyorick, marksg@dcs.shef.ac.uk AbstractExpand
Human Associations and the Choice of Features for Semantic Verb Classification ⋆ ⋆
This article investigates whether human associations to ve rbs as collected in a web experiment can help us to identify salient features for semantic v erb classes. Starting from the assumption thatExpand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 68 REFERENCES
Word-Sense Disambiguation Using Statistical Models of Roget’s Categories Trained on Large Corpora
TLDR
A program that disambiguates English word senses in unrestricted text using statistical models of the major Roget's Thesaurus categories, enabling training on unrestricted monolingual text without human intervention. Expand
From Grammar to Lexicon: Unsupervised Learning of Lexical Syntax
  • M. Brent
  • Computer Science
  • Comput. Linguistics
  • 1993
TLDR
This paper describes an approach based on two principles, rely on local morpho-syntactic cues to structure rather than trying to parse entire sentences, and treat these cues as probabilistic rather than absolute indicators of syntactic structure. Expand
Word Association Norms, Mutual Information and Lexicography
TLDR
The proposed measure, the association ratio, estimates word association norms directly from computer readable corpora, making it possible to estimate norms for tens of thousands of words. Expand
English Verb Classes and Alternations: A Preliminary Investigation
TLDR
Beth Levin shows how identifying verbs with similar syntactic behavior provides an effective means of distinguishing semantically coherent verb classes, and isolates these classes by examining verb behavior with respect to a wide range of syntactic alternations that reflect verb meaning. Expand
Subject-Dependent Co-Occurence and Word Sense Disambiguation
TLDR
Using the subject classifications given in the machine-redable version of Longman's Dictionary of Contemporary English, subject-dependent co-occurrence links between words of the defining vocabulary are established to construct "neighborhoods" and the application of these neighborhoods to information retrieval is described. Expand
The Acquisition of Lexical Knowledge from Combined Machine-Readable Dictionary Sources
TLDR
A software package for correlating MRDs based on sense merging techniques is described and it is shown how such a tool can be employed in augmenting a lexical knowledge base built from a conventional MRD with thesaurus information. Expand
Providing machine tractable dictionary tools
TLDR
This paper discusses three different but related large-scale computational methods to transform Mrds into Mtds, the Longman Dictionary of Contemporary English (Ldoce), which requires some handcoding of initial information but are largely automatic. Expand
Learnability and Cognition: The Acquisition of Argument Structure
Part 1 A learnability paradox: argument structure and the lexicon the logical problem of language acquisition Baker's paradox attempted solutions to Baker's paradox. Part 2 Constraints on lexicalExpand
ACQUIRING LEXICAL DATA FROM MACHINE-READABLE DICTIONARY RESOURCES FOR MACHINE TRANSLATION
This paper describes the direct and indirect automatic exploitation of multiple monolingual and bilingual machine-readable resources for acquiring lexical information, in (partial) real-time supportExpand
On Argument Structure
This chapter deals with argument structure, the relationship between the underlying semantics of the noun phrases associated with a verb and the form of their syntactic expression. It explores theExpand
...
1
2
3
4
5
...