• Corpus ID: 5087222

The English all-words task

@inproceedings{Snyder2004TheEA,
  title={The English all-words task},
  author={Benjamin Snyder and Martha Palmer},
  booktitle={SENSEVAL@ACL},
  year={2004}
}

Compression de vocabulaire de sens grâce aux relations sémantiques pour la désambiguïsation lexicale (Sense Vocabulary Compression through Semantic Knowledge for Word Sense Disambiguation)

Nos méthodes permettent de réduire considérablement the taille des modèles de DL neuronaux, avec l’avantage d’améliorer leur couverture sans données supplémentaires, and sans impacter leur précision.

A graph-based approach to word sense disambiguation. An unsupervised method based on semantic relatedness

A new method of combining similarity metrics that uses higher order relations between words to assign appropriate weights to each edge in the graph is introduced and a new approach for selecting the most appropriate sense of the target word that makes use of the in-degree centrality algorithm and senses of the neighbor words is proposed.

Evaluating the word-expert approach for Named-Entity Disambiguation

The results of the word-expert approach to NED are presented, where one classifier is built for each target entity mention string, as well as a study of the differences between WSD and NED, including ambiguity and synonymy statistics.

Unsupervised Word Sense Disambiguation Using Markov Random Field and Dependency Parser

This work model the WSD problem as a Maximum A Posteriori (MAP) Inference Query on a Markov Random Field (MRF) built using WordNet and Link Parser or Stanford Parser, and their combination of dependency and MRF is novel.

Unsupervised similarity-based word sense disambiguation using context vectors and sentential word importance

A new unsupervised similarity-based word sense disambiguation (WSD) algorithm that operates by computing the semantic similarity between glosses of the target word and a context vector, which enables it to utilize a higher degree of semantic information.

Significance of Novel WSD Algorithms

The strong POS + Frequency baseline is proposed as a basic easy-to-implement platform for testing how well algorithms can do when combined with other high-accuracy modules, and it is shown that significant and interesting algorithms exist.

Coarse Word-Sense Disambiguation Using Common Sense

This work has created a system for coarse word sense disambiguation using blending, a common sense reasoning technique, to combine information from SemCor, WordNet, ConceptNet and Extended WordNet to create a correct sense within that space.

Using Sense Clustering for the Disambiguation of Words (pp. 23-28)

The underlying idea is that the clustering of word senses provides a useful way to discover semantically related senses and this proposal regarding both fine- and coarse-grained disambiguation is evaluated.

Kernel Methods for Minimally Supervised WSD

A combination of basic kernel functions are used to independently estimate syntagmatic and domain similarity, building a set of word-expert classifiers that share a common domain model acquired from a large corpus of unlabeled data.
...

References

SHOWING 1-2 OF 2 REFERENCES

WordNet : an electronic lexical database

The lexical database: nouns in WordNet, Katherine J. Miller a semantic network of English verbs, and applications of WordNet: building semantic concordances are presented.

English Tasks: All-Words and Verb Lexical Sample

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.