@inproceedings{zeng-etal-2019-empirical,
title = "Empirical Evaluation of Active Learning Techniques for Neural {MT}",
author = "Zeng, Xiangkai and
Garg, Sarthak and
Chatterjee, Rajen and
Nallasamy, Udhyakumar and
Paulik, Matthias",
editor = "Cherry, Colin and
Durrett, Greg and
Foster, George and
Haffari, Reza and
Khadivi, Shahram and
Peng, Nanyun and
Ren, Xiang and
Swayamdipta, Swabha",
booktitle = "Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-6110",
doi = "10.18653/v1/D19-6110",
pages = "84--93",
abstract = "Active learning (AL) for machine translation (MT) has been well-studied for the phrase-based MT paradigm. Several AL algorithms for data sampling have been proposed over the years. However, given the rapid advancement in neural methods, these algorithms have not been thoroughly investigated in the context of neural MT (NMT). In this work, we address this missing aspect by conducting a systematic comparison of different AL methods in a simulated AL framework. Our experimental setup to compare different AL methods uses: i) State-of-the-art NMT architecture to achieve realistic results; and ii) the same dataset (WMT{'}13 English-Spanish) to have fair comparison across different methods. We then demonstrate how recent advancements in unsupervised pre-training and paraphrastic embedding can be used to improve existing AL methods. Finally, we propose a neural extension for an AL sampling method used in the context of phrase-based MT - Round Trip Translation Likelihood (RTTL). RTTL uses a bidirectional translation model to estimate the loss of information during translation and outperforms previous methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeng-etal-2019-empirical">
<titleInfo>
<title>Empirical Evaluation of Active Learning Techniques for Neural MT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiangkai</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarthak</namePart>
<namePart type="family">Garg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajen</namePart>
<namePart type="family">Chatterjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Udhyakumar</namePart>
<namePart type="family">Nallasamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Paulik</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 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Cherry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Durrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahram</namePart>
<namePart type="family">Khadivi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</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>Active learning (AL) for machine translation (MT) has been well-studied for the phrase-based MT paradigm. Several AL algorithms for data sampling have been proposed over the years. However, given the rapid advancement in neural methods, these algorithms have not been thoroughly investigated in the context of neural MT (NMT). In this work, we address this missing aspect by conducting a systematic comparison of different AL methods in a simulated AL framework. Our experimental setup to compare different AL methods uses: i) State-of-the-art NMT architecture to achieve realistic results; and ii) the same dataset (WMT’13 English-Spanish) to have fair comparison across different methods. We then demonstrate how recent advancements in unsupervised pre-training and paraphrastic embedding can be used to improve existing AL methods. Finally, we propose a neural extension for an AL sampling method used in the context of phrase-based MT - Round Trip Translation Likelihood (RTTL). RTTL uses a bidirectional translation model to estimate the loss of information during translation and outperforms previous methods.</abstract>
<identifier type="citekey">zeng-etal-2019-empirical</identifier>
<identifier type="doi">10.18653/v1/D19-6110</identifier>
<location>
<url>https://aclanthology.org/D19-6110</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>84</start>
<end>93</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Empirical Evaluation of Active Learning Techniques for Neural MT
%A Zeng, Xiangkai
%A Garg, Sarthak
%A Chatterjee, Rajen
%A Nallasamy, Udhyakumar
%A Paulik, Matthias
%Y Cherry, Colin
%Y Durrett, Greg
%Y Foster, George
%Y Haffari, Reza
%Y Khadivi, Shahram
%Y Peng, Nanyun
%Y Ren, Xiang
%Y Swayamdipta, Swabha
%S Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F zeng-etal-2019-empirical
%X Active learning (AL) for machine translation (MT) has been well-studied for the phrase-based MT paradigm. Several AL algorithms for data sampling have been proposed over the years. However, given the rapid advancement in neural methods, these algorithms have not been thoroughly investigated in the context of neural MT (NMT). In this work, we address this missing aspect by conducting a systematic comparison of different AL methods in a simulated AL framework. Our experimental setup to compare different AL methods uses: i) State-of-the-art NMT architecture to achieve realistic results; and ii) the same dataset (WMT’13 English-Spanish) to have fair comparison across different methods. We then demonstrate how recent advancements in unsupervised pre-training and paraphrastic embedding can be used to improve existing AL methods. Finally, we propose a neural extension for an AL sampling method used in the context of phrase-based MT - Round Trip Translation Likelihood (RTTL). RTTL uses a bidirectional translation model to estimate the loss of information during translation and outperforms previous methods.
%R 10.18653/v1/D19-6110
%U https://aclanthology.org/D19-6110
%U https://doi.org/10.18653/v1/D19-6110
%P 84-93
Markdown (Informal)
[Empirical Evaluation of Active Learning Techniques for Neural MT](https://aclanthology.org/D19-6110) (Zeng et al., 2019)
ACL
- Xiangkai Zeng, Sarthak Garg, Rajen Chatterjee, Udhyakumar Nallasamy, and Matthias Paulik. 2019. Empirical Evaluation of Active Learning Techniques for Neural MT. In Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019), pages 84–93, Hong Kong, China. Association for Computational Linguistics.