Boosting Tricks for Word Mover's Distance
Résumé
Word embeddings have opened a new path in creating novel approaches for addressing traditional problems in the natural language processing (NLP) domain. However, using word embeddings to compare text documents remains a relatively unexplored topic-with Word Mover's Distance (WMD) being the prominent tool used so far. In this paper, we present a variety of tools that can further improve the computation of distances between documents based on WMD. We demonstrate that, alternative stopwords, cross document-topic comparison, deep contextualized word vectors and convex metric learning, constitute powerful tools that can boost WMD.
Origine | Fichiers produits par l'(les) auteur(s) |
---|