@inproceedings{kumon-etal-2024-evaluating,
title = "Evaluating Structural Generalization in Neural Machine Translation",
author = "Kumon, Ryoma and
Matsuoka, Daiki and
Yanaka, Hitomi",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.783",
pages = "13220--13239",
abstract = "Compositional generalization refers to the ability to generalize to novel combinations of previously observed words and syntactic structures.Since it is regarded as a desired property of neural models, recent work has assessed compositional generalization in machine translation as well as semantic parsing.However, previous evaluations with machine translation have focused mostly on lexical generalization (i.e., generalization to unseen combinations of known words).Thus, it remains unclear to what extent models can translate sentences that require structural generalization (i.e., generalization to different sorts of syntactic structures).To address this question, we construct SGET, a machine translation dataset covering various types of compositional generalization with control of words and sentence structures.We evaluate neural machine translation models on SGET and show that they struggle more in structural generalization than in lexical generalization.We also find different performance trends in semantic parsing and machine translation, which indicates the importance of evaluations across various tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumon-etal-2024-evaluating">
<titleInfo>
<title>Evaluating Structural Generalization in Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ryoma</namePart>
<namePart type="family">Kumon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daiki</namePart>
<namePart type="family">Matsuoka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitomi</namePart>
<namePart type="family">Yanaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Compositional generalization refers to the ability to generalize to novel combinations of previously observed words and syntactic structures.Since it is regarded as a desired property of neural models, recent work has assessed compositional generalization in machine translation as well as semantic parsing.However, previous evaluations with machine translation have focused mostly on lexical generalization (i.e., generalization to unseen combinations of known words).Thus, it remains unclear to what extent models can translate sentences that require structural generalization (i.e., generalization to different sorts of syntactic structures).To address this question, we construct SGET, a machine translation dataset covering various types of compositional generalization with control of words and sentence structures.We evaluate neural machine translation models on SGET and show that they struggle more in structural generalization than in lexical generalization.We also find different performance trends in semantic parsing and machine translation, which indicates the importance of evaluations across various tasks.</abstract>
<identifier type="citekey">kumon-etal-2024-evaluating</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.783</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>13220</start>
<end>13239</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Structural Generalization in Neural Machine Translation
%A Kumon, Ryoma
%A Matsuoka, Daiki
%A Yanaka, Hitomi
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F kumon-etal-2024-evaluating
%X Compositional generalization refers to the ability to generalize to novel combinations of previously observed words and syntactic structures.Since it is regarded as a desired property of neural models, recent work has assessed compositional generalization in machine translation as well as semantic parsing.However, previous evaluations with machine translation have focused mostly on lexical generalization (i.e., generalization to unseen combinations of known words).Thus, it remains unclear to what extent models can translate sentences that require structural generalization (i.e., generalization to different sorts of syntactic structures).To address this question, we construct SGET, a machine translation dataset covering various types of compositional generalization with control of words and sentence structures.We evaluate neural machine translation models on SGET and show that they struggle more in structural generalization than in lexical generalization.We also find different performance trends in semantic parsing and machine translation, which indicates the importance of evaluations across various tasks.
%U https://aclanthology.org/2024.findings-acl.783
%P 13220-13239
Markdown (Informal)
[Evaluating Structural Generalization in Neural Machine Translation](https://aclanthology.org/2024.findings-acl.783) (Kumon et al., Findings 2024)
ACL