Is Singular Value Decomposition Useful for Word Similarity Extraction?

TítuloIs Singular Value Decomposition Useful for Word Similarity Extraction?
AutoresPablo Gamallo, Stefan Bordag
TipoArtículo de revista
Fonte Language Resources and Evaluation, Springer, Vol. 45, pp. 95-119 , 2011.
RankRanked Q1 in Language and Linguistics by CiteScore
DOI10.1007/s10579-010-9129-5
AbstractIn this paper, we analyze the behaviour of Singular Value Decomposition in a number of word similarity extraction tasks, namely acquisition of translation equivalents from comparable corpora. Special attention is paid to two different aspects: computational efficiency and extraction quality. The main objective of the paper is to describe several experiments comparing methods based on Singular Value Decomposition (SVD) to other strategies. The results lead us to conclude that SVD makes the extraction less computationally efficient and much less precise than other more basic models for the task of extracting translation equivalents from comparable corpora.
Palabras chaveInformation extraction, Word similarity, Comparable corpora, Singular value decomposition