Word sense disambiguation: A survey

@article{Navigli2009WordSD,
  title={Word sense disambiguation: A survey},
  author={R. Navigli},
  journal={ACM Comput. Surv.},
  year={2009},
  volume={41},
  pages={10:1-10:69}
}
  • R. Navigli
  • Published 1 February 2009
  • Computer Science
  • ACM Comput. Surv.
Word sense disambiguation (WSD) is the ability to identify the meaning of words in context in a computational manner. [...] Key Method We overview supervised, unsupervised, and knowledge-based approaches. The assessment of WSD systems is discussed in the context of the Senseval/Semeval campaigns, aiming at the objective evaluation of systems participating in several different disambiguation tasks. Finally, applications, open problems, and future directions are discussed.Expand
WSD-TIC: Word Sense Disambiguation Using Taxonomic Information Content
TLDR
This paper describes the proposed approach (WSD-TIC) which is based on the words surrounding the polysemous word in a context which is represented by a vector composed of weighted nouns using taxonomic information content.
Word Sense Disambiguation: A Briefly Survey
TLDR
The supervised, semi-supervised, unsupervised and knowledge-based approaches for WSD are discussed and an idea of few of the WSD algorithms is furnished.
Arabic word sense disambiguation: a review
  • Bilel Elayeb
  • Computer Science
    Artificial Intelligence Review
  • 2018
TLDR
The reader is introduced to the motivation for solving the ambiguity of Arabic words and a description of the task is detail, including supervised, unsupervised, semi-supervised and knowledge-based approaches.
A N E MPIRICAL STUDY OF WORD SENSE DISAMBIGUATION
Word Sense Disambiguation (WSD) is an important area which has an impact on improving the performance of applications of computational linguistics such as machine translation, information retrieval,
WordNet and Wiktionary-Based Approach for Word Sense Disambiguation
TLDR
The main emphasis of this paper is feature selection for disambiguation purpose, and the assessment of WSD systems is discussed in the context of the Senseval campaign, aiming at the objective evaluation of the proposal to the systems participating in several different disambigsuation tasks.
Practice of Word Sense Disambiguation
TLDR
The paper contains a brief introduction into WSD and describes the classical approaches to solve the problem and reports results of disambiguation that were achieved using a set of methods which are available on a widely acclaimed web site.
Word Sense Ambiguity: A Survey
TLDR
This paper discusses about the ambiguity and some important measures to deal with ambiguous statements and the computational identification of meaning for words in context.
A Survey on Supervised Learning for Word Sense Disambiguation
Word Sense Disambiguation (WSD) is the process of determining which sense of a word is used in a given context. Due to its importance in understanding semantics it is used in many real-world
Metaheuristic for Word Sense Disambiguation: a Review
TLDR
This paper aims to provide a review of several approaches to word Sense Disambiguation by tackling and categorizing the related works in accordance to the main types.
Transductive Learning Games for Word Sense Disambiguation
TLDR
Word Sense Disambiguation (WSD) is the task of identifying the intended sense of a word in a computational manner based on the context in which it appears, which is a central topic of this discipline.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 330 REFERENCES
Exploiting Parallel Texts for Word Sense Disambiguation: An Empirical Study
TLDR
This paper evaluates an approach to automatically acquire sense-tagged training data from English-Chinese parallel corpora, which are then used for disambiguating the nouns in the SENSEVAL-2 English lexical sample task.
The Interaction of Knowledge Sources in Word Sense Disambiguation
TLDR
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.
Contextual Word Sense Tuning and Disambiguation
TLDR
An integrated method based on a well-known lexical knowledge base and on corpus statistics is used to tune the sense classification to a specific sublanguage and to drive contextual disambiguation of word senses.
Learning Semantic Classes for Word Sense Disambiguation
TLDR
It is shown that these general concepts from a sense tagged corpus can be transformed to fine grained word senses using simple heuristics, and applying the technique for recent SENSEVAL data sets shows that this approach can yield state of the art performance.
Integrating Multiple Knowledge Sources to Disambiguate Word Sense: An Exemplar-Based Approach
TLDR
This approach integrates a diverse set of knowledge sources to disambiguate word sense, including part of speech of neighboring words, morphological form, the unordered set of surrounding words, local collocations, and verb-object syntactic relation.
Word-Sense Disambiguation for Machine Translation
TLDR
It is shown that the word-translation system can be used to improve performance on a simplified machine-translation task and can effectively and accurately prune the set of candidate translations for a word.
Exploring Automatic Word Sense Disambiguation with Decision Lists and the Web
TLDR
An in-depth study of the performance of decision lists on two publicly available corpora and an additional corpus automatically acquired from the Web, using the fine-grained highly polysemous senses in WordNet, reveals that SemCor can be an acceptable starting point for an all-words system.
A method for disambiguating word senses in a large corpus
TLDR
The proposed method was designed to disambiguate senses that are usually associated with different topics using a Bayesian argument that has been applied successfully in related tasks such as author identification and information retrieval.
Word Sense Disambiguation within a Multilingual Framework
TLDR
A practical and functional implementation of a basic idea common to research interest in defining word meanings in cross-linguistic terms, SALAAM for Sense Assignment Leveraging Alignment And Multilinguality, is proposed as a means of improving its performance on sense disambiguation for verbs in particular and other word types in general.
A structural approach to the automatic adjudication of word sense disagreements
  • R. Navigli
  • Computer Science
    Natural Language Engineering
  • 2008
Abstract The semantic annotation of texts with senses from a computational lexicon is a complex and often subjective task. As a matter of fact, the fine granularity of the WordNet sense inventory
...
1
2
3
4
5
...