@inproceedings{zheng-etal-2019-simpler,
title = "Simpler and Faster Learning of Adaptive Policies for Simultaneous Translation",
author = "Zheng, Baigong and
Zheng, Renjie and
Ma, Mingbo and
Huang, Liang",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1137",
doi = "10.18653/v1/D19-1137",
pages = "1349--1354",
abstract = "Simultaneous translation is widely useful but remains challenging. Previous work falls into two main categories: (a) fixed-latency policies such as Ma et al. (2019) and (b) adaptive policies such as Gu et al. (2017). The former are simple and effective, but have to aggressively predict future content due to diverging source-target word order; the latter do not anticipate, but suffer from unstable and inefficient training. To combine the merits of both approaches, we propose a simple supervised-learning framework to learn an adaptive policy from oracle READ/WRITE sequences generated from parallel text. At each step, such an oracle sequence chooses to WRITE the next target word if the available source sentence context provides enough information to do so, otherwise READ the next source word. Experiments on German{\textless}={\textgreater}English show that our method, without retraining the underlying NMT model, can learn flexible policies with better BLEU scores and similar latencies compared to previous work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-etal-2019-simpler">
<titleInfo>
<title>Simpler and Faster Learning of Adaptive Policies for Simultaneous Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Baigong</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Renjie</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingbo</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Simultaneous translation is widely useful but remains challenging. Previous work falls into two main categories: (a) fixed-latency policies such as Ma et al. (2019) and (b) adaptive policies such as Gu et al. (2017). The former are simple and effective, but have to aggressively predict future content due to diverging source-target word order; the latter do not anticipate, but suffer from unstable and inefficient training. To combine the merits of both approaches, we propose a simple supervised-learning framework to learn an adaptive policy from oracle READ/WRITE sequences generated from parallel text. At each step, such an oracle sequence chooses to WRITE the next target word if the available source sentence context provides enough information to do so, otherwise READ the next source word. Experiments on German\textless=\textgreaterEnglish show that our method, without retraining the underlying NMT model, can learn flexible policies with better BLEU scores and similar latencies compared to previous work.</abstract>
<identifier type="citekey">zheng-etal-2019-simpler</identifier>
<identifier type="doi">10.18653/v1/D19-1137</identifier>
<location>
<url>https://aclanthology.org/D19-1137</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>1349</start>
<end>1354</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simpler and Faster Learning of Adaptive Policies for Simultaneous Translation
%A Zheng, Baigong
%A Zheng, Renjie
%A Ma, Mingbo
%A Huang, Liang
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F zheng-etal-2019-simpler
%X Simultaneous translation is widely useful but remains challenging. Previous work falls into two main categories: (a) fixed-latency policies such as Ma et al. (2019) and (b) adaptive policies such as Gu et al. (2017). The former are simple and effective, but have to aggressively predict future content due to diverging source-target word order; the latter do not anticipate, but suffer from unstable and inefficient training. To combine the merits of both approaches, we propose a simple supervised-learning framework to learn an adaptive policy from oracle READ/WRITE sequences generated from parallel text. At each step, such an oracle sequence chooses to WRITE the next target word if the available source sentence context provides enough information to do so, otherwise READ the next source word. Experiments on German\textless=\textgreaterEnglish show that our method, without retraining the underlying NMT model, can learn flexible policies with better BLEU scores and similar latencies compared to previous work.
%R 10.18653/v1/D19-1137
%U https://aclanthology.org/D19-1137
%U https://doi.org/10.18653/v1/D19-1137
%P 1349-1354
Markdown (Informal)
[Simpler and Faster Learning of Adaptive Policies for Simultaneous Translation](https://aclanthology.org/D19-1137) (Zheng et al., EMNLP-IJCNLP 2019)
ACL
- Baigong Zheng, Renjie Zheng, Mingbo Ma, and Liang Huang. 2019. Simpler and Faster Learning of Adaptive Policies for Simultaneous Translation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1349–1354, Hong Kong, China. Association for Computational Linguistics.