@inproceedings{kiyono-etal-2018-unsupervised,
title = "Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder Models",
author = "Kiyono, Shun and
Takase, Sho and
Suzuki, Jun and
Okazaki, Naoaki and
Inui, Kentaro and
Nagata, Masaaki",
editor = "Linzen, Tal and
Chrupa{\l}a, Grzegorz and
Alishahi, Afra",
booktitle = "Proceedings of the 2018 {EMNLP} Workshop {B}lackbox{NLP}: Analyzing and Interpreting Neural Networks for {NLP}",
month = nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-5410",
doi = "10.18653/v1/W18-5410",
pages = "74--81",
abstract = "Developing a method for understanding the inner workings of black-box neural methods is an important research endeavor. Conventionally, many studies have used an attention matrix to interpret how Encoder-Decoder-based models translate a given source sentence to the corresponding target sentence. However, recent studies have empirically revealed that an attention matrix is not optimal for token-wise translation analyses. We propose a method that explicitly models the token-wise alignment between the source and target sequences to provide a better analysis. Experiments show that our method can acquire token-wise alignments that are superior to those of an attention mechanism.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kiyono-etal-2018-unsupervised">
<titleInfo>
<title>Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shun</namePart>
<namePart type="family">Kiyono</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sho</namePart>
<namePart type="family">Takase</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masaaki</namePart>
<namePart type="family">Nagata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tal</namePart>
<namePart type="family">Linzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grzegorz</namePart>
<namePart type="family">Chrupała</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Afra</namePart>
<namePart type="family">Alishahi</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>Developing a method for understanding the inner workings of black-box neural methods is an important research endeavor. Conventionally, many studies have used an attention matrix to interpret how Encoder-Decoder-based models translate a given source sentence to the corresponding target sentence. However, recent studies have empirically revealed that an attention matrix is not optimal for token-wise translation analyses. We propose a method that explicitly models the token-wise alignment between the source and target sequences to provide a better analysis. Experiments show that our method can acquire token-wise alignments that are superior to those of an attention mechanism.</abstract>
<identifier type="citekey">kiyono-etal-2018-unsupervised</identifier>
<identifier type="doi">10.18653/v1/W18-5410</identifier>
<location>
<url>https://aclanthology.org/W18-5410</url>
</location>
<part>
<date>2018-11</date>
<extent unit="page">
<start>74</start>
<end>81</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder Models
%A Kiyono, Shun
%A Takase, Sho
%A Suzuki, Jun
%A Okazaki, Naoaki
%A Inui, Kentaro
%A Nagata, Masaaki
%Y Linzen, Tal
%Y Chrupała, Grzegorz
%Y Alishahi, Afra
%S Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
%D 2018
%8 November
%I Association for Computational Linguistics
%C Brussels, Belgium
%F kiyono-etal-2018-unsupervised
%X Developing a method for understanding the inner workings of black-box neural methods is an important research endeavor. Conventionally, many studies have used an attention matrix to interpret how Encoder-Decoder-based models translate a given source sentence to the corresponding target sentence. However, recent studies have empirically revealed that an attention matrix is not optimal for token-wise translation analyses. We propose a method that explicitly models the token-wise alignment between the source and target sequences to provide a better analysis. Experiments show that our method can acquire token-wise alignments that are superior to those of an attention mechanism.
%R 10.18653/v1/W18-5410
%U https://aclanthology.org/W18-5410
%U https://doi.org/10.18653/v1/W18-5410
%P 74-81
Markdown (Informal)
[Unsupervised Token-wise Alignment to Improve Interpretation of Encoder-Decoder Models](https://aclanthology.org/W18-5410) (Kiyono et al., EMNLP 2018)
ACL