@inproceedings{li-etal-2024-non,
title = "Non-Autoregressive Machine Translation as Constrained {HMM}",
author = "Li, Haoran and
Jie, Zhanming and
Lu, Wei",
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.735",
pages = "12361--12372",
abstract = "In non-autoregressive translation (NAT), directed acyclic Transformers (DAT) have demonstrated their ability to achieve comparable performance to the autoregressive Transformers.In this paper, we first show that DAT is essentially a fully connected left-to-right Hidden Markov Model (HMM), with the source and target sequences being observations and the token positions being latent states.Even though generative models like HMM do not suffer from label bias in traditional task settings (e.g., sequence labeling), we argue here that the left-to-right HMM in NAT may still encounter this issue due to the missing observations at the inference stage.To combat label bias, we propose two constrained HMMs: 1) Adaptive Window HMM, which explicitly balances the number of outgoing transitions at different states; 2) Bi-directional HMM, i.e., a combination of left-to-right and right-to-left HMMs, whose uni-directional components can implicitly regularize each other{'}s biases via shared parameters.Experimental results on WMT{'}14 EnDe and WMT{'}17 ZhEn demonstrate that our methods can achieve better or comparable performance to the original DAT using various decoding methods.We also demonstrate that our methods effectively reduce the impact of label bias.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2024-non">
<titleInfo>
<title>Non-Autoregressive Machine Translation as Constrained HMM</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haoran</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhanming</namePart>
<namePart type="family">Jie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Lu</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>In non-autoregressive translation (NAT), directed acyclic Transformers (DAT) have demonstrated their ability to achieve comparable performance to the autoregressive Transformers.In this paper, we first show that DAT is essentially a fully connected left-to-right Hidden Markov Model (HMM), with the source and target sequences being observations and the token positions being latent states.Even though generative models like HMM do not suffer from label bias in traditional task settings (e.g., sequence labeling), we argue here that the left-to-right HMM in NAT may still encounter this issue due to the missing observations at the inference stage.To combat label bias, we propose two constrained HMMs: 1) Adaptive Window HMM, which explicitly balances the number of outgoing transitions at different states; 2) Bi-directional HMM, i.e., a combination of left-to-right and right-to-left HMMs, whose uni-directional components can implicitly regularize each other’s biases via shared parameters.Experimental results on WMT’14 EnDe and WMT’17 ZhEn demonstrate that our methods can achieve better or comparable performance to the original DAT using various decoding methods.We also demonstrate that our methods effectively reduce the impact of label bias.</abstract>
<identifier type="citekey">li-etal-2024-non</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.735</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>12361</start>
<end>12372</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Non-Autoregressive Machine Translation as Constrained HMM
%A Li, Haoran
%A Jie, Zhanming
%A Lu, Wei
%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 li-etal-2024-non
%X In non-autoregressive translation (NAT), directed acyclic Transformers (DAT) have demonstrated their ability to achieve comparable performance to the autoregressive Transformers.In this paper, we first show that DAT is essentially a fully connected left-to-right Hidden Markov Model (HMM), with the source and target sequences being observations and the token positions being latent states.Even though generative models like HMM do not suffer from label bias in traditional task settings (e.g., sequence labeling), we argue here that the left-to-right HMM in NAT may still encounter this issue due to the missing observations at the inference stage.To combat label bias, we propose two constrained HMMs: 1) Adaptive Window HMM, which explicitly balances the number of outgoing transitions at different states; 2) Bi-directional HMM, i.e., a combination of left-to-right and right-to-left HMMs, whose uni-directional components can implicitly regularize each other’s biases via shared parameters.Experimental results on WMT’14 EnDe and WMT’17 ZhEn demonstrate that our methods can achieve better or comparable performance to the original DAT using various decoding methods.We also demonstrate that our methods effectively reduce the impact of label bias.
%U https://aclanthology.org/2024.findings-acl.735
%P 12361-12372
Markdown (Informal)
[Non-Autoregressive Machine Translation as Constrained HMM](https://aclanthology.org/2024.findings-acl.735) (Li et al., Findings 2024)
ACL