@inproceedings{chen-etal-2021-mask,
title = "Mask-Align: Self-Supervised Neural Word Alignment",
author = "Chen, Chi and
Sun, Maosong and
Liu, Yang",
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.369",
doi = "10.18653/v1/2021.acl-long.369",
pages = "4781--4791",
abstract = "Word alignment, which aims to align translationally equivalent words between source and target sentences, plays an important role in many natural language processing tasks. Current unsupervised neural alignment methods focus on inducing alignments from neural machine translation models, which does not leverage the full context in the target sequence. In this paper, we propose Mask-Align, a self-supervised word alignment model that takes advantage of the full context on the target side. Our model masks out each target token and predicts it conditioned on both source and the remaining target tokens. This two-step process is based on the assumption that the source token contributing most to recovering the masked target token should be aligned. We also introduce an attention variant called leaky attention, which alleviates the problem of unexpected high cross-attention weights on special tokens such as periods. Experiments on four language pairs show that our model outperforms previous unsupervised neural aligners and obtains new state-of-the-art results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2021-mask">
<titleInfo>
<title>Mask-Align: Self-Supervised Neural Word Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>Word alignment, which aims to align translationally equivalent words between source and target sentences, plays an important role in many natural language processing tasks. Current unsupervised neural alignment methods focus on inducing alignments from neural machine translation models, which does not leverage the full context in the target sequence. In this paper, we propose Mask-Align, a self-supervised word alignment model that takes advantage of the full context on the target side. Our model masks out each target token and predicts it conditioned on both source and the remaining target tokens. This two-step process is based on the assumption that the source token contributing most to recovering the masked target token should be aligned. We also introduce an attention variant called leaky attention, which alleviates the problem of unexpected high cross-attention weights on special tokens such as periods. Experiments on four language pairs show that our model outperforms previous unsupervised neural aligners and obtains new state-of-the-art results.</abstract>
<identifier type="citekey">chen-etal-2021-mask</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.369</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.369</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>4781</start>
<end>4791</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mask-Align: Self-Supervised Neural Word Alignment
%A Chen, Chi
%A Sun, Maosong
%A Liu, Yang
%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 chen-etal-2021-mask
%X Word alignment, which aims to align translationally equivalent words between source and target sentences, plays an important role in many natural language processing tasks. Current unsupervised neural alignment methods focus on inducing alignments from neural machine translation models, which does not leverage the full context in the target sequence. In this paper, we propose Mask-Align, a self-supervised word alignment model that takes advantage of the full context on the target side. Our model masks out each target token and predicts it conditioned on both source and the remaining target tokens. This two-step process is based on the assumption that the source token contributing most to recovering the masked target token should be aligned. We also introduce an attention variant called leaky attention, which alleviates the problem of unexpected high cross-attention weights on special tokens such as periods. Experiments on four language pairs show that our model outperforms previous unsupervised neural aligners and obtains new state-of-the-art results.
%R 10.18653/v1/2021.acl-long.369
%U https://aclanthology.org/2021.acl-long.369
%U https://doi.org/10.18653/v1/2021.acl-long.369
%P 4781-4791
Markdown (Informal)
[Mask-Align: Self-Supervised Neural Word Alignment](https://aclanthology.org/2021.acl-long.369) (Chen et al., ACL-IJCNLP 2021)
ACL
- Chi Chen, Maosong Sun, and Yang Liu. 2021. Mask-Align: Self-Supervised Neural Word Alignment. 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 4781–4791, Online. Association for Computational Linguistics.