@inproceedings{akyurek-andreas-2021-lexicon,
title = "Lexicon Learning for Few Shot Sequence Modeling",
author = "Akyurek, Ekin and
Andreas, Jacob",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.382",
doi = "10.18653/v1/2021.acl-long.382",
pages = "4934--4946",
abstract = "Sequence-to-sequence transduction is the core problem in language processing applications as diverse as semantic parsing, machine translation, and instruction following. The neural network models that provide the dominant solution to these problems are brittle, especially in low-resource settings: they fail to generalize correctly or systematically from small datasets. Past work has shown that many failures of systematic generalization arise from neural models{'} inability to disentangle lexical phenomena from syntactic ones. To address this, we augment neural decoders with a lexical translation mechanism that generalizes existing copy mechanisms to incorporate learned, decontextualized, token-level translation rules. We describe how to initialize this mechanism using a variety of lexicon learning algorithms, and show that it improves systematic generalization on a diverse set of sequence modeling tasks drawn from cognitive science, formal semantics, and machine translation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akyurek-andreas-2021-lexicon">
<titleInfo>
<title>Lexicon Learning for Few Shot Sequence Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekin</namePart>
<namePart type="family">Akyurek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacob</namePart>
<namePart type="family">Andreas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sequence-to-sequence transduction is the core problem in language processing applications as diverse as semantic parsing, machine translation, and instruction following. The neural network models that provide the dominant solution to these problems are brittle, especially in low-resource settings: they fail to generalize correctly or systematically from small datasets. Past work has shown that many failures of systematic generalization arise from neural models’ inability to disentangle lexical phenomena from syntactic ones. To address this, we augment neural decoders with a lexical translation mechanism that generalizes existing copy mechanisms to incorporate learned, decontextualized, token-level translation rules. We describe how to initialize this mechanism using a variety of lexicon learning algorithms, and show that it improves systematic generalization on a diverse set of sequence modeling tasks drawn from cognitive science, formal semantics, and machine translation.</abstract>
<identifier type="citekey">akyurek-andreas-2021-lexicon</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.382</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.382</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>4934</start>
<end>4946</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lexicon Learning for Few Shot Sequence Modeling
%A Akyurek, Ekin
%A Andreas, Jacob
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F akyurek-andreas-2021-lexicon
%X Sequence-to-sequence transduction is the core problem in language processing applications as diverse as semantic parsing, machine translation, and instruction following. The neural network models that provide the dominant solution to these problems are brittle, especially in low-resource settings: they fail to generalize correctly or systematically from small datasets. Past work has shown that many failures of systematic generalization arise from neural models’ inability to disentangle lexical phenomena from syntactic ones. To address this, we augment neural decoders with a lexical translation mechanism that generalizes existing copy mechanisms to incorporate learned, decontextualized, token-level translation rules. We describe how to initialize this mechanism using a variety of lexicon learning algorithms, and show that it improves systematic generalization on a diverse set of sequence modeling tasks drawn from cognitive science, formal semantics, and machine translation.
%R 10.18653/v1/2021.acl-long.382
%U https://aclanthology.org/2021.acl-long.382
%U https://doi.org/10.18653/v1/2021.acl-long.382
%P 4934-4946
Markdown (Informal)
[Lexicon Learning for Few Shot Sequence Modeling](https://aclanthology.org/2021.acl-long.382) (Akyurek & Andreas, ACL-IJCNLP 2021)
ACL
- Ekin Akyurek and Jacob Andreas. 2021. Lexicon Learning for Few Shot Sequence Modeling. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4934–4946, Online. Association for Computational Linguistics.