Refining Raw Sentence Representations for Textual Entailment Recognition via Attention

Jorge Balazs, Edison Marrese-Taylor, Pablo Loyola, Yutaka Matsuo


Abstract
In this paper we present the model used by the team Rivercorners for the 2017 RepEval shared task. First, our model separately encodes a pair of sentences into variable-length representations by using a bidirectional LSTM. Later, it creates fixed-length raw representations by means of simple aggregation functions, which are then refined using an attention mechanism. Finally it combines the refined representations of both sentences into a single vector to be used for classification. With this model we obtained test accuracies of 72.057% and 72.055% in the matched and mismatched evaluation tracks respectively, outperforming the LSTM baseline, and obtaining performances similar to a model that relies on shared information between sentences (ESIM). When using an ensemble both accuracies increased to 72.247% and 72.827% respectively.
Anthology ID:
W17-5310
Volume:
Proceedings of the 2nd Workshop on Evaluating Vector Space Representations for NLP
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venues:
RepEval | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
51–55
Language:
URL:
https://www.aclweb.org/anthology/W17-5310
DOI:
10.18653/v1/W17-5310
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W17-5310.pdf