@inproceedings{yang-etal-2020-streaming,
title = "A Streaming Approach For Efficient Batched Beam Search",
author = "Yang, Kevin and
Yao, Violet and
DeNero, John and
Klein, Dan",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.366",
doi = "10.18653/v1/2020.emnlp-main.366",
pages = "4526--4535",
abstract = "We propose an efficient batching strategy for variable-length decoding on GPU architectures. During decoding, when candidates terminate or are pruned according to heuristics, our streaming approach periodically {``}refills{''} the batch before proceeding with a selected subset of candidates. We apply our method to variable-width beam search on a state-of-the-art machine translation model. Our method decreases runtime by up to 71{\%} compared to a fixed-width beam search baseline and 17{\%} compared to a variable-width baseline, while matching baselines{'} BLEU. Finally, experiments show that our method can speed up decoding in other domains, such as semantic and syntactic parsing.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2020-streaming">
<titleInfo>
<title>A Streaming Approach For Efficient Batched Beam Search</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">DeNero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Klein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>We propose an efficient batching strategy for variable-length decoding on GPU architectures. During decoding, when candidates terminate or are pruned according to heuristics, our streaming approach periodically “refills” the batch before proceeding with a selected subset of candidates. We apply our method to variable-width beam search on a state-of-the-art machine translation model. Our method decreases runtime by up to 71% compared to a fixed-width beam search baseline and 17% compared to a variable-width baseline, while matching baselines’ BLEU. Finally, experiments show that our method can speed up decoding in other domains, such as semantic and syntactic parsing.</abstract>
<identifier type="citekey">yang-etal-2020-streaming</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.366</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.366</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>4526</start>
<end>4535</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Streaming Approach For Efficient Batched Beam Search
%A Yang, Kevin
%A Yao, Violet
%A DeNero, John
%A Klein, Dan
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F yang-etal-2020-streaming
%X We propose an efficient batching strategy for variable-length decoding on GPU architectures. During decoding, when candidates terminate or are pruned according to heuristics, our streaming approach periodically “refills” the batch before proceeding with a selected subset of candidates. We apply our method to variable-width beam search on a state-of-the-art machine translation model. Our method decreases runtime by up to 71% compared to a fixed-width beam search baseline and 17% compared to a variable-width baseline, while matching baselines’ BLEU. Finally, experiments show that our method can speed up decoding in other domains, such as semantic and syntactic parsing.
%R 10.18653/v1/2020.emnlp-main.366
%U https://aclanthology.org/2020.emnlp-main.366
%U https://doi.org/10.18653/v1/2020.emnlp-main.366
%P 4526-4535
Markdown (Informal)
[A Streaming Approach For Efficient Batched Beam Search](https://aclanthology.org/2020.emnlp-main.366) (Yang et al., EMNLP 2020)
ACL
- Kevin Yang, Violet Yao, John DeNero, and Dan Klein. 2020. A Streaming Approach For Efficient Batched Beam Search. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4526–4535, Online. Association for Computational Linguistics.