papers AI Learner
The Github is limit! Click to go to the new site.

Expansional Retrofitting for Word Vector Enrichment


Abstract

Retrofitting techniques, which inject external resources into word representations, have compensated the weakness of distributed representations in semantic and relational knowledge between words. Implicitly retrofitting word vectors by expansional technique outperforms retrofitting in word similarity tasks with word vector generalization. In this paper, we propose unsupervised extrofitting: expansional retrofitting (extrofitting) without external semantic lexicons. We also propose deep extrofitting: in-depth stacking of extrofitting and further combinations of extrofitting with retrofitting. When experimenting with GloVe, we show that our methods outperform the previous methods on most of word similarity tasks while requiring only synonyms as an external resource. Lastly, we show the effect of word vector enrichment on text classification task, as a downstream task.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1808.07337

PDF

http://arxiv.org/pdf/1808.07337


Similar Posts

Comments