@inproceedings{balazs-etal-2017-refining,
title = "Refining Raw Sentence Representations for Textual Entailment Recognition via Attention",
author = "Balazs, Jorge and
Marrese-Taylor, Edison and
Loyola, Pablo and
Matsuo, Yutaka",
editor = "Bowman, Samuel and
Goldberg, Yoav and
Hill, Felix and
Lazaridou, Angeliki and
Levy, Omer and
Reichart, Roi and
S{\o}gaard, Anders",
booktitle = "Proceedings of the 2nd Workshop on Evaluating Vector Space Representations for {NLP}",
month = sep,
year = "2017",
address = "Copenhagen, Denmark",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-5310",
doi = "10.18653/v1/W17-5310",
pages = "51--55",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="balazs-etal-2017-refining">
<titleInfo>
<title>Refining Raw Sentence Representations for Textual Entailment Recognition via Attention</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Balazs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edison</namePart>
<namePart type="family">Marrese-Taylor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pablo</namePart>
<namePart type="family">Loyola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yutaka</namePart>
<namePart type="family">Matsuo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Evaluating Vector Space Representations for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Bowman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felix</namePart>
<namePart type="family">Hill</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angeliki</namePart>
<namePart type="family">Lazaridou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omer</namePart>
<namePart type="family">Levy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roi</namePart>
<namePart type="family">Reichart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anders</namePart>
<namePart type="family">Søgaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Copenhagen, Denmark</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">balazs-etal-2017-refining</identifier>
<identifier type="doi">10.18653/v1/W17-5310</identifier>
<location>
<url>https://aclanthology.org/W17-5310</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>51</start>
<end>55</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Refining Raw Sentence Representations for Textual Entailment Recognition via Attention
%A Balazs, Jorge
%A Marrese-Taylor, Edison
%A Loyola, Pablo
%A Matsuo, Yutaka
%Y Bowman, Samuel
%Y Goldberg, Yoav
%Y Hill, Felix
%Y Lazaridou, Angeliki
%Y Levy, Omer
%Y Reichart, Roi
%Y Søgaard, Anders
%S Proceedings of the 2nd Workshop on Evaluating Vector Space Representations for NLP
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F balazs-etal-2017-refining
%X 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.
%R 10.18653/v1/W17-5310
%U https://aclanthology.org/W17-5310
%U https://doi.org/10.18653/v1/W17-5310
%P 51-55
Markdown (Informal)
[Refining Raw Sentence Representations for Textual Entailment Recognition via Attention](https://aclanthology.org/W17-5310) (Balazs et al., RepEval 2017)
ACL