@inproceedings{zhang-etal-2022-study,
title = "A Study of Syntactic Multi-Modality in Non-Autoregressive Machine Translation",
author = "Zhang, Kexun and
Wang, Rui and
Tan, Xu and
Guo, Junliang and
Ren, Yi and
Qin, Tao and
Liu, Tie-Yan",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.126/",
doi = "10.18653/v1/2022.naacl-main.126",
pages = "1747--1757",
abstract = "It is difficult for non-autoregressive translation (NAT) models to capture the multi-modal distribution of target translations due to their conditional independence assumption, which is known as the {\textquotedblleft}multi-modality problem{\textquotedblright}, including the lexical multi-modality and the syntactic multi-modality. While the first one has been well studied, the syntactic multi-modality brings severe challenges to the standard cross entropy (XE) loss in NAT and is understudied. In this paper, we conduct a systematic study on the syntactic multi-modality problem. Specifically, we decompose it into short- and long-range syntactic multi-modalities and evaluate several recent NAT algorithms with advanced loss functions on both carefully designed synthesized datasets and real datasets. We find that the Connectionist Temporal Classification (CTC) loss and the Order-Agnostic Cross Entropy (OAXE) loss can better handle short- and long-range syntactic multi-modalities respectively. Furthermore, we take the best of both and design a new loss function to better handle the complicated syntactic multi-modality in real-world datasets. To facilitate practical usage, we provide a guide to using different loss functions for different kinds of syntactic multi-modality."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2022-study">
<titleInfo>
<title>A Study of Syntactic Multi-Modality in Non-Autoregressive Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kexun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junliang</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tie-Yan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>It is difficult for non-autoregressive translation (NAT) models to capture the multi-modal distribution of target translations due to their conditional independence assumption, which is known as the “multi-modality problem”, including the lexical multi-modality and the syntactic multi-modality. While the first one has been well studied, the syntactic multi-modality brings severe challenges to the standard cross entropy (XE) loss in NAT and is understudied. In this paper, we conduct a systematic study on the syntactic multi-modality problem. Specifically, we decompose it into short- and long-range syntactic multi-modalities and evaluate several recent NAT algorithms with advanced loss functions on both carefully designed synthesized datasets and real datasets. We find that the Connectionist Temporal Classification (CTC) loss and the Order-Agnostic Cross Entropy (OAXE) loss can better handle short- and long-range syntactic multi-modalities respectively. Furthermore, we take the best of both and design a new loss function to better handle the complicated syntactic multi-modality in real-world datasets. To facilitate practical usage, we provide a guide to using different loss functions for different kinds of syntactic multi-modality.</abstract>
<identifier type="citekey">zhang-etal-2022-study</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.126</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.126/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1747</start>
<end>1757</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Study of Syntactic Multi-Modality in Non-Autoregressive Machine Translation
%A Zhang, Kexun
%A Wang, Rui
%A Tan, Xu
%A Guo, Junliang
%A Ren, Yi
%A Qin, Tao
%A Liu, Tie-Yan
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F zhang-etal-2022-study
%X It is difficult for non-autoregressive translation (NAT) models to capture the multi-modal distribution of target translations due to their conditional independence assumption, which is known as the “multi-modality problem”, including the lexical multi-modality and the syntactic multi-modality. While the first one has been well studied, the syntactic multi-modality brings severe challenges to the standard cross entropy (XE) loss in NAT and is understudied. In this paper, we conduct a systematic study on the syntactic multi-modality problem. Specifically, we decompose it into short- and long-range syntactic multi-modalities and evaluate several recent NAT algorithms with advanced loss functions on both carefully designed synthesized datasets and real datasets. We find that the Connectionist Temporal Classification (CTC) loss and the Order-Agnostic Cross Entropy (OAXE) loss can better handle short- and long-range syntactic multi-modalities respectively. Furthermore, we take the best of both and design a new loss function to better handle the complicated syntactic multi-modality in real-world datasets. To facilitate practical usage, we provide a guide to using different loss functions for different kinds of syntactic multi-modality.
%R 10.18653/v1/2022.naacl-main.126
%U https://aclanthology.org/2022.naacl-main.126/
%U https://doi.org/10.18653/v1/2022.naacl-main.126
%P 1747-1757
Markdown (Informal)
[A Study of Syntactic Multi-Modality in Non-Autoregressive Machine Translation](https://aclanthology.org/2022.naacl-main.126/) (Zhang et al., NAACL 2022)
ACL
- Kexun Zhang, Rui Wang, Xu Tan, Junliang Guo, Yi Ren, Tao Qin, and Tie-Yan Liu. 2022. A Study of Syntactic Multi-Modality in Non-Autoregressive Machine Translation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1747–1757, Seattle, United States. Association for Computational Linguistics.