Predicting the relevance of distributional semantic similarity with contextual information

Abstract : Using distributional analysis methods to compute semantic proximity links between words has become commonplace in NLP. The resulting relations are often noisy or difficult to interpret in general. This paper focuses on the issues of evaluating a distributional resource and filtering the relations it contains, but instead of considering it in abstracto, we focus on pairs of words in context. In a discourse , we are interested in knowing if the semantic link between two items is a by-product of textual coherence or is irrelevant. We first set up a human annotation of semantic links with or without contex-tual information to show the importance of the textual context in evaluating the relevance of semantic similarity, and to assess the prevalence of actual semantic relations between word tokens. We then built an experiment to automatically predict this relevance , evaluated on the reliable reference data set which was the outcome of the first annotation. We show that in-document information greatly improve the prediction made by the similarity level alone.
Complete list of metadatas

Cited literature [35 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01259674
Contributor : Cécile Fabre <>
Submitted on : Tuesday, January 26, 2016 - 6:04:38 PM
Last modification on : Friday, June 14, 2019 - 6:31:09 PM
Long-term archiving on : Wednesday, April 27, 2016 - 1:20:55 PM

File

P14-1045.pdf
Publisher files allowed on an open archive

Identifiers

Collections

Citation

Philippe Muller, Cécile Fabre, Clémentine Adam. Predicting the relevance of distributional semantic similarity with contextual information. Annual Meeting of the Association for Computational Linguistics (ACL 2014),, Jun 2014, Baltimore, United States. ⟨10.3115/v1/P14-1045⟩. ⟨hal-01259674⟩

Share

Metrics

Record views

343

Files downloads

161