@inproceedings{lee-etal-2021-discriminative,
title = "Discriminative Reranking for Neural Machine Translation",
author = "Lee, Ann and
Auli, Michael and
Ranzato, Marc{'}Aurelio",
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.563",
doi = "10.18653/v1/2021.acl-long.563",
pages = "7250--7264",
abstract = "Reranking models enable the integration of rich features to select a better output hypothesis within an n-best list or lattice. These models have a long history in NLP, and we revisit discriminative reranking for modern neural machine translation models by training a large transformer architecture. This takes as input both the source sentence as well as a list of hypotheses to output a ranked list. The reranker is trained to predict the observed distribution of a desired metric, e.g. BLEU, over the n-best list. Since such a discriminator contains hundreds of millions of parameters, we improve its generalization using pre-training and data augmentation techniques. Experiments on four WMT directions show that our discriminative reranking approach is effective and complementary to existing generative reranking approaches, yielding improvements of up to 4 BLEU over the beam search output.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2021-discriminative">
<titleInfo>
<title>Discriminative Reranking for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ann</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Auli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marc’Aurelio</namePart>
<namePart type="family">Ranzato</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>Reranking models enable the integration of rich features to select a better output hypothesis within an n-best list or lattice. These models have a long history in NLP, and we revisit discriminative reranking for modern neural machine translation models by training a large transformer architecture. This takes as input both the source sentence as well as a list of hypotheses to output a ranked list. The reranker is trained to predict the observed distribution of a desired metric, e.g. BLEU, over the n-best list. Since such a discriminator contains hundreds of millions of parameters, we improve its generalization using pre-training and data augmentation techniques. Experiments on four WMT directions show that our discriminative reranking approach is effective and complementary to existing generative reranking approaches, yielding improvements of up to 4 BLEU over the beam search output.</abstract>
<identifier type="citekey">lee-etal-2021-discriminative</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.563</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.563</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>7250</start>
<end>7264</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Discriminative Reranking for Neural Machine Translation
%A Lee, Ann
%A Auli, Michael
%A Ranzato, Marc’Aurelio
%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 lee-etal-2021-discriminative
%X Reranking models enable the integration of rich features to select a better output hypothesis within an n-best list or lattice. These models have a long history in NLP, and we revisit discriminative reranking for modern neural machine translation models by training a large transformer architecture. This takes as input both the source sentence as well as a list of hypotheses to output a ranked list. The reranker is trained to predict the observed distribution of a desired metric, e.g. BLEU, over the n-best list. Since such a discriminator contains hundreds of millions of parameters, we improve its generalization using pre-training and data augmentation techniques. Experiments on four WMT directions show that our discriminative reranking approach is effective and complementary to existing generative reranking approaches, yielding improvements of up to 4 BLEU over the beam search output.
%R 10.18653/v1/2021.acl-long.563
%U https://aclanthology.org/2021.acl-long.563
%U https://doi.org/10.18653/v1/2021.acl-long.563
%P 7250-7264
Markdown (Informal)
[Discriminative Reranking for Neural Machine Translation](https://aclanthology.org/2021.acl-long.563) (Lee et al., ACL-IJCNLP 2021)
ACL
- Ann Lee, Michael Auli, and Marc’Aurelio Ranzato. 2021. Discriminative Reranking for Neural Machine Translation. 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 7250–7264, Online. Association for Computational Linguistics.