@inproceedings{yu-etal-2024-context,
title = "Context-Aware Non-Autoregressive Document-Level Translation with Sentence-Aligned Connectionist Temporal Classification",
author = "Yu, Hao and
Huang, Kaiyu and
Zhao, Anqi and
Liu, Junpeng and
Huang, Degen",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.337/",
pages = "3812--3824",
abstract = "Previous studies employ the autoregressive translation (AT) paradigm in the document-to-document neural machine translation. These methods extend the translation unit from a single sentence to a pseudo-document and encodes the full pseudo-document, avoiding the redundant computation problem in context. However, the AT methods cannot parallelize decoding and struggle with error accumulation, especially when the length of sentences increases. In this work, we propose a context-aware non-autoregressive framework with the sentence-aligned connectionist temporal classification (SA-CTC) loss for document-level neural machine translation. In particular, the SA-CTC loss reduces the search space of the decoding path by fixing the positions of the beginning and end tokens for each sentence in the document. Meanwhile, the context-aware architecture introduces preset nodes to represent sentence-level information and utilizes a hierarchical attention structure to regulate the attention hypothesis space. Experimental results show that our proposed method can achieve competitive performance compared with several strong baselines. Our method implements non-autoregressive modeling in Doc-to-Doc translation manner, achieving an average 46X decoding speedup compared to the document-level AT baselines on three benchmarks."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2024-context">
<titleInfo>
<title>Context-Aware Non-Autoregressive Document-Level Translation with Sentence-Aligned Connectionist Temporal Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaiyu</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anqi</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junpeng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Degen</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Previous studies employ the autoregressive translation (AT) paradigm in the document-to-document neural machine translation. These methods extend the translation unit from a single sentence to a pseudo-document and encodes the full pseudo-document, avoiding the redundant computation problem in context. However, the AT methods cannot parallelize decoding and struggle with error accumulation, especially when the length of sentences increases. In this work, we propose a context-aware non-autoregressive framework with the sentence-aligned connectionist temporal classification (SA-CTC) loss for document-level neural machine translation. In particular, the SA-CTC loss reduces the search space of the decoding path by fixing the positions of the beginning and end tokens for each sentence in the document. Meanwhile, the context-aware architecture introduces preset nodes to represent sentence-level information and utilizes a hierarchical attention structure to regulate the attention hypothesis space. Experimental results show that our proposed method can achieve competitive performance compared with several strong baselines. Our method implements non-autoregressive modeling in Doc-to-Doc translation manner, achieving an average 46X decoding speedup compared to the document-level AT baselines on three benchmarks.</abstract>
<identifier type="citekey">yu-etal-2024-context</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.337/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>3812</start>
<end>3824</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Context-Aware Non-Autoregressive Document-Level Translation with Sentence-Aligned Connectionist Temporal Classification
%A Yu, Hao
%A Huang, Kaiyu
%A Zhao, Anqi
%A Liu, Junpeng
%A Huang, Degen
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F yu-etal-2024-context
%X Previous studies employ the autoregressive translation (AT) paradigm in the document-to-document neural machine translation. These methods extend the translation unit from a single sentence to a pseudo-document and encodes the full pseudo-document, avoiding the redundant computation problem in context. However, the AT methods cannot parallelize decoding and struggle with error accumulation, especially when the length of sentences increases. In this work, we propose a context-aware non-autoregressive framework with the sentence-aligned connectionist temporal classification (SA-CTC) loss for document-level neural machine translation. In particular, the SA-CTC loss reduces the search space of the decoding path by fixing the positions of the beginning and end tokens for each sentence in the document. Meanwhile, the context-aware architecture introduces preset nodes to represent sentence-level information and utilizes a hierarchical attention structure to regulate the attention hypothesis space. Experimental results show that our proposed method can achieve competitive performance compared with several strong baselines. Our method implements non-autoregressive modeling in Doc-to-Doc translation manner, achieving an average 46X decoding speedup compared to the document-level AT baselines on three benchmarks.
%U https://aclanthology.org/2024.lrec-main.337/
%P 3812-3824
Markdown (Informal)
[Context-Aware Non-Autoregressive Document-Level Translation with Sentence-Aligned Connectionist Temporal Classification](https://aclanthology.org/2024.lrec-main.337/) (Yu et al., LREC-COLING 2024)
ACL