@inproceedings{strobelt-etal-2018-debugging,
title = "Debugging Sequence-to-Sequence Models with {S}eq2{S}eq-Vis",
author = "Strobelt, Hendrik and
Gehrmann, Sebastian and
Behrisch, Michael and
Perer, Adam and
Pfister, Hanspeter and
Rush, Alexander",
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/W18-5451",
doi = "10.18653/v1/W18-5451",
pages = "368--370",
abstract = "Neural attention-based sequence-to-sequence models (seq2seq) (Sutskever et al., 2014; Bahdanau et al., 2014) have proven to be accurate and robust for many sequence prediction tasks. They have become the standard approach for automatic translation of text, at the cost of increased model complexity and uncertainty. End-to-end trained neural models act as a black box, which makes it difficult to examine model decisions and attribute errors to a specific part of a model. The highly connected and high-dimensional internal representations pose a challenge for analysis and visualization tools. The development of methods to understand seq2seq predictions is crucial for systems in production settings, as mistakes involving language are often very apparent to human readers. For instance, a widely publicized incident resulted from a translation system mistakenly translating {``}good morning{''} into {``}attack them{''} leading to a wrongful arrest (Hern, 2017).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="strobelt-etal-2018-debugging">
<titleInfo>
<title>Debugging Sequence-to-Sequence Models with Seq2Seq-Vis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hendrik</namePart>
<namePart type="family">Strobelt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Behrisch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Perer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanspeter</namePart>
<namePart type="family">Pfister</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Rush</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>Neural attention-based sequence-to-sequence models (seq2seq) (Sutskever et al., 2014; Bahdanau et al., 2014) have proven to be accurate and robust for many sequence prediction tasks. They have become the standard approach for automatic translation of text, at the cost of increased model complexity and uncertainty. End-to-end trained neural models act as a black box, which makes it difficult to examine model decisions and attribute errors to a specific part of a model. The highly connected and high-dimensional internal representations pose a challenge for analysis and visualization tools. The development of methods to understand seq2seq predictions is crucial for systems in production settings, as mistakes involving language are often very apparent to human readers. For instance, a widely publicized incident resulted from a translation system mistakenly translating “good morning” into “attack them” leading to a wrongful arrest (Hern, 2017).</abstract>
<identifier type="citekey">strobelt-etal-2018-debugging</identifier>
<identifier type="doi">10.18653/v1/W18-5451</identifier>
<location>
<url>https://aclanthology.org/W18-5451</url>
</location>
<part>
<date>2018-11</date>
<extent unit="page">
<start>368</start>
<end>370</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Debugging Sequence-to-Sequence Models with Seq2Seq-Vis
%A Strobelt, Hendrik
%A Gehrmann, Sebastian
%A Behrisch, Michael
%A Perer, Adam
%A Pfister, Hanspeter
%A Rush, Alexander
%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 strobelt-etal-2018-debugging
%X Neural attention-based sequence-to-sequence models (seq2seq) (Sutskever et al., 2014; Bahdanau et al., 2014) have proven to be accurate and robust for many sequence prediction tasks. They have become the standard approach for automatic translation of text, at the cost of increased model complexity and uncertainty. End-to-end trained neural models act as a black box, which makes it difficult to examine model decisions and attribute errors to a specific part of a model. The highly connected and high-dimensional internal representations pose a challenge for analysis and visualization tools. The development of methods to understand seq2seq predictions is crucial for systems in production settings, as mistakes involving language are often very apparent to human readers. For instance, a widely publicized incident resulted from a translation system mistakenly translating “good morning” into “attack them” leading to a wrongful arrest (Hern, 2017).
%R 10.18653/v1/W18-5451
%U https://aclanthology.org/W18-5451
%U https://doi.org/10.18653/v1/W18-5451
%P 368-370
Markdown (Informal)
[Debugging Sequence-to-Sequence Models with Seq2Seq-Vis](https://aclanthology.org/W18-5451) (Strobelt et al., EMNLP 2018)
ACL
- Hendrik Strobelt, Sebastian Gehrmann, Michael Behrisch, Adam Perer, Hanspeter Pfister, and Alexander Rush. 2018. Debugging Sequence-to-Sequence Models with Seq2Seq-Vis. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 368–370, Brussels, Belgium. Association for Computational Linguistics.