arXiv Analytics

Sign in

arXiv:1907.08184 [cs.CL]AbstractReferencesReviewsResources

Evaluating the Utility of Document Embedding Vector Difference for Relation Learning

Jingyuan Zhang, Timothy Baldwin

Published 2019-07-18Version 1

Recent work has demonstrated that vector offsets obtained by subtracting pretrained word embedding vectors can be used to predict lexical relations with surprising accuracy. Inspired by this finding, in this paper, we extend the idea to the document level, in generating document-level embeddings, calculating the distance between them, and using a linear classifier to classify the relation between the documents. In the context of duplicate detection and dialogue act tagging tasks, we show that document-level difference vectors have utility in assessing document-level similarity, but perform less well in multi-relational classification.

Related articles:
arXiv:1906.03158 [cs.CL] (Published 2019-06-07)
Matching the Blanks: Distributional Similarity for Relation Learning