@inproceedings{bao-etal-2020-university,
title = "The {U}niversity of {M}aryland{'}s Submissions to the {WMT}20 Chat Translation Task: Searching for More Data to Adapt Discourse-Aware Neural Machine Translation",
author = "Bao, Calvin and
Shiue, Yow-Ting and
Song, Chujun and
Li, Jie and
Carpuat, Marine",
booktitle = "Proceedings of the Fifth Conference on Machine Translation",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.wmt-1.56",
pages = "456--461",
abstract = "This paper describes the University of Maryland{'}s submissions to the WMT20 Shared Task on Chat Translation. We focus on translating agent-side utterances from English to German. We started from an off-the-shelf BPE-based standard transformer model trained with WMT17 news and fine-tuned it with the provided in-domain training data. In addition, we augment the training set with its best matches in the WMT19 news dataset. Our primary submission uses a standard Transformer, while our contrastive submissions use multi-encoder Transformers to attend to previous utterances. Our primary submission achieves 56.7 BLEU on the agent side (en→de), outperforming a baseline system provided by the task organizers by more than 13 BLEU points. Moreover, according to an evaluation on a set of carefully-designed examples, the multi-encoder architecture is able to generate more coherent translations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bao-etal-2020-university">
<titleInfo>
<title>The University of Maryland’s Submissions to the WMT20 Chat Translation Task: Searching for More Data to Adapt Discourse-Aware Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Calvin</namePart>
<namePart type="family">Bao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yow-Ting</namePart>
<namePart type="family">Shiue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chujun</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Conference on Machine Translation</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the University of Maryland’s submissions to the WMT20 Shared Task on Chat Translation. We focus on translating agent-side utterances from English to German. We started from an off-the-shelf BPE-based standard transformer model trained with WMT17 news and fine-tuned it with the provided in-domain training data. In addition, we augment the training set with its best matches in the WMT19 news dataset. Our primary submission uses a standard Transformer, while our contrastive submissions use multi-encoder Transformers to attend to previous utterances. Our primary submission achieves 56.7 BLEU on the agent side (en→de), outperforming a baseline system provided by the task organizers by more than 13 BLEU points. Moreover, according to an evaluation on a set of carefully-designed examples, the multi-encoder architecture is able to generate more coherent translations.</abstract>
<identifier type="citekey">bao-etal-2020-university</identifier>
<location>
<url>https://aclanthology.org/2020.wmt-1.56</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>456</start>
<end>461</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The University of Maryland’s Submissions to the WMT20 Chat Translation Task: Searching for More Data to Adapt Discourse-Aware Neural Machine Translation
%A Bao, Calvin
%A Shiue, Yow-Ting
%A Song, Chujun
%A Li, Jie
%A Carpuat, Marine
%S Proceedings of the Fifth Conference on Machine Translation
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F bao-etal-2020-university
%X This paper describes the University of Maryland’s submissions to the WMT20 Shared Task on Chat Translation. We focus on translating agent-side utterances from English to German. We started from an off-the-shelf BPE-based standard transformer model trained with WMT17 news and fine-tuned it with the provided in-domain training data. In addition, we augment the training set with its best matches in the WMT19 news dataset. Our primary submission uses a standard Transformer, while our contrastive submissions use multi-encoder Transformers to attend to previous utterances. Our primary submission achieves 56.7 BLEU on the agent side (en→de), outperforming a baseline system provided by the task organizers by more than 13 BLEU points. Moreover, according to an evaluation on a set of carefully-designed examples, the multi-encoder architecture is able to generate more coherent translations.
%U https://aclanthology.org/2020.wmt-1.56
%P 456-461
Markdown (Informal)
[The University of Maryland’s Submissions to the WMT20 Chat Translation Task: Searching for More Data to Adapt Discourse-Aware Neural Machine Translation](https://aclanthology.org/2020.wmt-1.56) (Bao et al., WMT 2020)
ACL