Verb Class Disambiguation Using Informative Priors

Lapata, Mirella; Brew, Chris

doi:10.1162/089120104773633385

Cited by 36 publications

(36 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It only requires raw text from the given domain and because of this it can easily be applied to a new domain, or sense inventory, given sufficient text. Lapata and Brew (2004) have recently also highlighted the importance of a good prior in WSD. They used syntactic evidence to find a prior distribution for verb classes, based on (Levin, 1993), and incorporate this in a WSD system.…”

Section: Related Workmentioning

confidence: 99%

Finding predominant word senses in untagged text

McCarthy

Koeling

Weeds

et al. 2004

Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics - ACL '04

193

233

View full text Add to dashboard Cite

In word sense disambiguation (WSD), the heuristic of choosing the most common sense is extremely powerful because the distribution of the senses of a word is often skewed. The problem with using the predominant, or first sense heuristic, aside from the fact that it does not take surrounding context into account, is that it assumes some quantity of handtagged data. Whilst there are a few hand-tagged corpora available for some languages, one would expect the frequency distribution of the senses of words, particularly topical words, to depend on the genre and domain of the text under consideration. We present work on the use of a thesaurus acquired from raw textual corpora and the WordNet similarity package to find predominant noun senses automatically. The acquired predominant senses give a precision of 64% on the nouns of the SENSEVAL-2 English all-words task. This is a very promising result given that our method does not require any hand-tagged text, such as SemCor. Furthermore, we demonstrate that our method discovers appropriate predominant senses for words from two domainspecific corpora.

show abstract

Section: Related Workmentioning

confidence: 99%

Finding predominant word senses in untagged text

McCarthy

Koeling

Weeds

et al. 2004

Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics - ACL '04

193

233

View full text Add to dashboard Cite

show abstract

“…We also evaluate our induced verb classes on this gold-standard data, which was created on the basis of Levin's classes (Levin, 1993). Lapata and Brew (2004) and Li and Brew (2007) proposed probabilistic models for calculating prior probabilities of verb classes for a verb. These models are approximated to condition not on verbs but on subcategorization frames.…”

Section: Related Workmentioning

confidence: 99%

A Step-wise Usage-based Method for Inducing Polysemy-aware Verb Classes

Kawahara¹,

Peterson

Palmer

2014

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

We present an unsupervised method for inducing verb classes from verb uses in gigaword corpora. Our method consists of two clustering steps: verb-specific semantic frames are first induced by clustering verb uses in a corpus and then verb classes are induced by clustering these frames. By taking this step-wise approach, we can not only generate verb classes based on a massive amount of verb uses in a scalable manner, but also deal with verb polysemy, which is bypassed by most of the previous studies on verb clustering. In our experiments, we acquire semantic frames and verb classes from two giga-word corpora, the larger comprising 20 billion words. The effectiveness of our approach is verified through quantitative evaluations based on polysemy-aware gold-standard data.

show abstract

“…Various approaches have been adopted, such as normalizing sense ranking scores to obtain a probability distribution (Jin et al, 2009), using subcategorisation information as an indication of verb sense (Lapata and Brew, 2004) or alternatively using parallel text (Chan and Ng, 2005;Chan and Ng, 2006;Agirre and Martinez, 2004).…”

Section: Background and Related Workmentioning

confidence: 99%

“…Such an approach requires knowledge of predominant senses; however, word sense distributions -and predominant senses toovary from corpus to corpus. Therefore, methods for automatically learning predominant senses and sense distributions for specific corpora are required (Koeling et al, 2005;Lapata and Brew, 2004).…”

Section: Introductionmentioning

confidence: 99%

Learning Word Sense Distributions, Detecting Unattested Senses and Identifying Novel Senses Using Topic Models

Lau¹,

Cook²,

McCarthy³

et al. 2014

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

Unsupervised word sense disambiguation (WSD) methods are an attractive approach to all-words WSD due to their non-reliance on expensive annotated data. Unsupervised estimates of sense frequency have been shown to be very useful for WSD due to the skewed nature of word sense distributions. This paper presents a fully unsupervised topic modelling-based approach to sense frequency estimation, which is highly portable to different corpora and sense inventories, in being applicable to any part of speech, and not requiring a hierarchical sense inventory, parsing or parallel text. We demonstrate the effectiveness of the method over the tasks of predominant sense learning and sense distribution acquisition, and also the novel tasks of detecting senses which aren't attested in the corpus, and identifying novel senses in the corpus which aren't captured in the sense inventory.

show abstract

Verb Class Disambiguation Using Informative Priors

Cited by 36 publications

References 18 publications

Finding predominant word senses in untagged text

Finding predominant word senses in untagged text

A Step-wise Usage-based Method for Inducing Polysemy-aware Verb Classes

Learning Word Sense Distributions, Detecting Unattested Senses and Identifying Novel Senses Using Topic Models

Contact Info

Product

Resources

About