@inproceedings{ren-etal-2021-semface,
title = "{S}em{F}ace: Pre-training Encoder and Decoder with a Semantic Interface for Neural Machine Translation",
author = "Ren, Shuo and
Zhou, Long and
Liu, Shujie and
Wei, Furu and
Zhou, Ming and
Ma, Shuai",
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.348/",
doi = "10.18653/v1/2021.acl-long.348",
pages = "4518--4527",
abstract = "While pre-training techniques are working very well in natural language processing, how to pre-train a decoder and effectively use it for neural machine translation (NMT) still remains a tricky issue. The main reason is that the cross-attention module between the encoder and decoder cannot be pre-trained, and the combined encoder-decoder model cannot work well in the fine-tuning stage because the inputs of the decoder cross-attention come from unknown encoder outputs. In this paper, we propose a better pre-training method for NMT by defining a semantic interface (SemFace) between the pre-trained encoder and the pre-trained decoder. Specifically, we propose two types of semantic interfaces, including CL-SemFace which regards cross-lingual embeddings as an interface, and VQ-SemFace which employs vector quantized embeddings to constrain the encoder outputs and decoder inputs in the same language-independent space. We conduct massive experiments on six supervised translation pairs and three unsupervised pairs. Experimental results demonstrate that our proposed SemFace can effectively connect the pre-trained encoder and decoder, and achieves significant improvement by 3.7 and 1.5 BLEU points on the two tasks respectively compared with previous pre-training-based NMT models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ren-etal-2021-semface">
<titleInfo>
<title>SemFace: Pre-training Encoder and Decoder with a Semantic Interface for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuo</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Long</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shujie</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Furu</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuai</namePart>
<namePart type="family">Ma</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>While pre-training techniques are working very well in natural language processing, how to pre-train a decoder and effectively use it for neural machine translation (NMT) still remains a tricky issue. The main reason is that the cross-attention module between the encoder and decoder cannot be pre-trained, and the combined encoder-decoder model cannot work well in the fine-tuning stage because the inputs of the decoder cross-attention come from unknown encoder outputs. In this paper, we propose a better pre-training method for NMT by defining a semantic interface (SemFace) between the pre-trained encoder and the pre-trained decoder. Specifically, we propose two types of semantic interfaces, including CL-SemFace which regards cross-lingual embeddings as an interface, and VQ-SemFace which employs vector quantized embeddings to constrain the encoder outputs and decoder inputs in the same language-independent space. We conduct massive experiments on six supervised translation pairs and three unsupervised pairs. Experimental results demonstrate that our proposed SemFace can effectively connect the pre-trained encoder and decoder, and achieves significant improvement by 3.7 and 1.5 BLEU points on the two tasks respectively compared with previous pre-training-based NMT models.</abstract>
<identifier type="citekey">ren-etal-2021-semface</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.348</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.348/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>4518</start>
<end>4527</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SemFace: Pre-training Encoder and Decoder with a Semantic Interface for Neural Machine Translation
%A Ren, Shuo
%A Zhou, Long
%A Liu, Shujie
%A Wei, Furu
%A Zhou, Ming
%A Ma, Shuai
%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 ren-etal-2021-semface
%X While pre-training techniques are working very well in natural language processing, how to pre-train a decoder and effectively use it for neural machine translation (NMT) still remains a tricky issue. The main reason is that the cross-attention module between the encoder and decoder cannot be pre-trained, and the combined encoder-decoder model cannot work well in the fine-tuning stage because the inputs of the decoder cross-attention come from unknown encoder outputs. In this paper, we propose a better pre-training method for NMT by defining a semantic interface (SemFace) between the pre-trained encoder and the pre-trained decoder. Specifically, we propose two types of semantic interfaces, including CL-SemFace which regards cross-lingual embeddings as an interface, and VQ-SemFace which employs vector quantized embeddings to constrain the encoder outputs and decoder inputs in the same language-independent space. We conduct massive experiments on six supervised translation pairs and three unsupervised pairs. Experimental results demonstrate that our proposed SemFace can effectively connect the pre-trained encoder and decoder, and achieves significant improvement by 3.7 and 1.5 BLEU points on the two tasks respectively compared with previous pre-training-based NMT models.
%R 10.18653/v1/2021.acl-long.348
%U https://aclanthology.org/2021.acl-long.348/
%U https://doi.org/10.18653/v1/2021.acl-long.348
%P 4518-4527
Markdown (Informal)
[SemFace: Pre-training Encoder and Decoder with a Semantic Interface for Neural Machine Translation](https://aclanthology.org/2021.acl-long.348/) (Ren et al., ACL-IJCNLP 2021)
ACL