@inproceedings{tay-etal-2018-co,
title = "Co-Stack Residual Affinity Networks with Multi-level Attention Refinement for Matching Text Sequences",
author = "Tay, Yi and
Luu, Anh Tuan and
Hui, Siu Cheung",
editor = "Riloff, Ellen and
Chiang, David and
Hockenmaier, Julia and
Tsujii, Jun{'}ichi",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1479",
doi = "10.18653/v1/D18-1479",
pages = "4492--4502",
abstract = "Learning a matching function between two text sequences is a long standing problem in NLP research. This task enables many potential applications such as question answering and paraphrase identification. This paper proposes Co-Stack Residual Affinity Networks (CSRAN), a new and universal neural architecture for this problem. CSRAN is a deep architecture, involving stacked (multi-layered) recurrent encoders. Stacked/Deep architectures are traditionally difficult to train, due to the inherent weaknesses such as difficulty with feature propagation and vanishing gradients. CSRAN incorporates two novel components to take advantage of the stacked architecture. Firstly, it introduces a new bidirectional alignment mechanism that learns affinity weights by fusing sequence pairs across stacked hierarchies. Secondly, it leverages a multi-level attention refinement component between stacked recurrent layers. The key intuition is that, by leveraging information across all network hierarchies, we can not only improve gradient flow but also improve overall performance. We conduct extensive experiments on six well-studied text sequence matching datasets, achieving state-of-the-art performance on all.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tay-etal-2018-co">
<titleInfo>
<title>Co-Stack Residual Affinity Networks with Multi-level Attention Refinement for Matching Text Sequences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Tay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anh</namePart>
<namePart type="given">Tuan</namePart>
<namePart type="family">Luu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siu</namePart>
<namePart type="given">Cheung</namePart>
<namePart type="family">Hui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hockenmaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun’ichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Learning a matching function between two text sequences is a long standing problem in NLP research. This task enables many potential applications such as question answering and paraphrase identification. This paper proposes Co-Stack Residual Affinity Networks (CSRAN), a new and universal neural architecture for this problem. CSRAN is a deep architecture, involving stacked (multi-layered) recurrent encoders. Stacked/Deep architectures are traditionally difficult to train, due to the inherent weaknesses such as difficulty with feature propagation and vanishing gradients. CSRAN incorporates two novel components to take advantage of the stacked architecture. Firstly, it introduces a new bidirectional alignment mechanism that learns affinity weights by fusing sequence pairs across stacked hierarchies. Secondly, it leverages a multi-level attention refinement component between stacked recurrent layers. The key intuition is that, by leveraging information across all network hierarchies, we can not only improve gradient flow but also improve overall performance. We conduct extensive experiments on six well-studied text sequence matching datasets, achieving state-of-the-art performance on all.</abstract>
<identifier type="citekey">tay-etal-2018-co</identifier>
<identifier type="doi">10.18653/v1/D18-1479</identifier>
<location>
<url>https://aclanthology.org/D18-1479</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>4492</start>
<end>4502</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Co-Stack Residual Affinity Networks with Multi-level Attention Refinement for Matching Text Sequences
%A Tay, Yi
%A Luu, Anh Tuan
%A Hui, Siu Cheung
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F tay-etal-2018-co
%X Learning a matching function between two text sequences is a long standing problem in NLP research. This task enables many potential applications such as question answering and paraphrase identification. This paper proposes Co-Stack Residual Affinity Networks (CSRAN), a new and universal neural architecture for this problem. CSRAN is a deep architecture, involving stacked (multi-layered) recurrent encoders. Stacked/Deep architectures are traditionally difficult to train, due to the inherent weaknesses such as difficulty with feature propagation and vanishing gradients. CSRAN incorporates two novel components to take advantage of the stacked architecture. Firstly, it introduces a new bidirectional alignment mechanism that learns affinity weights by fusing sequence pairs across stacked hierarchies. Secondly, it leverages a multi-level attention refinement component between stacked recurrent layers. The key intuition is that, by leveraging information across all network hierarchies, we can not only improve gradient flow but also improve overall performance. We conduct extensive experiments on six well-studied text sequence matching datasets, achieving state-of-the-art performance on all.
%R 10.18653/v1/D18-1479
%U https://aclanthology.org/D18-1479
%U https://doi.org/10.18653/v1/D18-1479
%P 4492-4502
Markdown (Informal)
[Co-Stack Residual Affinity Networks with Multi-level Attention Refinement for Matching Text Sequences](https://aclanthology.org/D18-1479) (Tay et al., EMNLP 2018)
ACL