Learning Phrase Embeddings from Paraphrases with GRUs

Zhihao Zhou, Lifu Huang, Heng Ji


Abstract
Learning phrase representations has been widely explored in many Natural Language Processing tasks (e.g., Sentiment Analysis, Machine Translation) and has shown promising improvements. Previous studies either learn non-compositional phrase representations with general word embedding learning techniques or learn compositional phrase representations based on syntactic structures, which either require huge amounts of human annotations or cannot be easily generalized to all phrases. In this work, we propose to take advantage of large-scaled paraphrase database and present a pairwise-GRU framework to generate compositional phrase representations. Our framework can be re-used to generate representations for any phrases. Experimental results show that our framework achieves state-of-the-art results on several phrase similarity tasks.
Anthology ID:
W17-5603
Volume:
Proceedings of the First Workshop on Curation and Applications of Parallel and Comparable Corpora
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Venue:
WS
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
16–23
Language:
URL:
https://www.aclweb.org/anthology/W17-5603
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W17-5603.pdf