@inproceedings{shao-etal-2019-aggregating,
title = "Aggregating Bidirectional Encoder Representations Using {M}atch{LSTM} for Sequence Matching",
author = "Shao, Bo and
Gong, Yeyun and
Qi, Weizhen and
Duan, Nan and
Lin, Xiaola",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1626",
doi = "10.18653/v1/D19-1626",
pages = "6059--6063",
abstract = "In this work, we propose an aggregation method to combine the Bidirectional Encoder Representations from Transformer (BERT) with a MatchLSTM layer for Sequence Matching. Given a sentence pair, we extract the output representations of it from BERT. Then we extend BERT with a MatchLSTM layer to get further interaction of the sentence pair for sequence matching tasks. Taking natural language inference as an example, we split BERT output into two parts, which is from premise sentence and hypothesis sentence. At each position of the hypothesis sentence, both the weighted representation of the premise sentence and the representation of the current token are fed into LSTM. We jointly train the aggregation layer and pre-trained layer for sequence matching. We conduct an experiment on two publicly available datasets, WikiQA and SNLI. Experiments show that our model achieves significantly improvement compared with state-of-the-art methods on both datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shao-etal-2019-aggregating">
<titleInfo>
<title>Aggregating Bidirectional Encoder Representations Using MatchLSTM for Sequence Matching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Shao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yeyun</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weizhen</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaola</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we propose an aggregation method to combine the Bidirectional Encoder Representations from Transformer (BERT) with a MatchLSTM layer for Sequence Matching. Given a sentence pair, we extract the output representations of it from BERT. Then we extend BERT with a MatchLSTM layer to get further interaction of the sentence pair for sequence matching tasks. Taking natural language inference as an example, we split BERT output into two parts, which is from premise sentence and hypothesis sentence. At each position of the hypothesis sentence, both the weighted representation of the premise sentence and the representation of the current token are fed into LSTM. We jointly train the aggregation layer and pre-trained layer for sequence matching. We conduct an experiment on two publicly available datasets, WikiQA and SNLI. Experiments show that our model achieves significantly improvement compared with state-of-the-art methods on both datasets.</abstract>
<identifier type="citekey">shao-etal-2019-aggregating</identifier>
<identifier type="doi">10.18653/v1/D19-1626</identifier>
<location>
<url>https://aclanthology.org/D19-1626</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>6059</start>
<end>6063</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Aggregating Bidirectional Encoder Representations Using MatchLSTM for Sequence Matching
%A Shao, Bo
%A Gong, Yeyun
%A Qi, Weizhen
%A Duan, Nan
%A Lin, Xiaola
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F shao-etal-2019-aggregating
%X In this work, we propose an aggregation method to combine the Bidirectional Encoder Representations from Transformer (BERT) with a MatchLSTM layer for Sequence Matching. Given a sentence pair, we extract the output representations of it from BERT. Then we extend BERT with a MatchLSTM layer to get further interaction of the sentence pair for sequence matching tasks. Taking natural language inference as an example, we split BERT output into two parts, which is from premise sentence and hypothesis sentence. At each position of the hypothesis sentence, both the weighted representation of the premise sentence and the representation of the current token are fed into LSTM. We jointly train the aggregation layer and pre-trained layer for sequence matching. We conduct an experiment on two publicly available datasets, WikiQA and SNLI. Experiments show that our model achieves significantly improvement compared with state-of-the-art methods on both datasets.
%R 10.18653/v1/D19-1626
%U https://aclanthology.org/D19-1626
%U https://doi.org/10.18653/v1/D19-1626
%P 6059-6063
Markdown (Informal)
[Aggregating Bidirectional Encoder Representations Using MatchLSTM for Sequence Matching](https://aclanthology.org/D19-1626) (Shao et al., EMNLP-IJCNLP 2019)
ACL