@inproceedings{mayhew-etal-2020-simultaneous,
title = "Simultaneous Translation and Paraphrase for Language Education",
author = "Mayhew, Stephen and
Bicknell, Klinton and
Brust, Chris and
McDowell, Bill and
Monroe, Will and
Settles, Burr",
booktitle = "Proceedings of the Fourth Workshop on Neural Generation and Translation",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.ngt-1.28",
doi = "10.18653/v1/2020.ngt-1.28",
pages = "232--243",
abstract = "We present the task of Simultaneous Translation and Paraphrasing for Language Education (STAPLE). Given a prompt in one language, the goal is to generate a diverse set of correct translations that language learners are likely to produce. This is motivated by the need to create and maintain large, high-quality sets of acceptable translations for exercises in a language-learning application, and synthesizes work spanning machine translation, MT evaluation, automatic paraphrasing, and language education technology. We developed a novel corpus with unique properties for five languages (Hungarian, Japanese, Korean, Portuguese, and Vietnamese), and report on the results of a shared task challenge which attracted 20 teams to solve the task. In our meta-analysis, we focus on three aspects of the resulting systems: external training corpus selection, model architecture and training decisions, and decoding and filtering strategies. We find that strong systems start with a large amount of generic training data, and then fine-tune with in-domain data, sampled according to our provided learner response frequencies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mayhew-etal-2020-simultaneous">
<titleInfo>
<title>Simultaneous Translation and Paraphrase for Language Education</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Mayhew</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Klinton</namePart>
<namePart type="family">Bicknell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Brust</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bill</namePart>
<namePart type="family">McDowell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Will</namePart>
<namePart type="family">Monroe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Burr</namePart>
<namePart type="family">Settles</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Neural Generation and 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>We present the task of Simultaneous Translation and Paraphrasing for Language Education (STAPLE). Given a prompt in one language, the goal is to generate a diverse set of correct translations that language learners are likely to produce. This is motivated by the need to create and maintain large, high-quality sets of acceptable translations for exercises in a language-learning application, and synthesizes work spanning machine translation, MT evaluation, automatic paraphrasing, and language education technology. We developed a novel corpus with unique properties for five languages (Hungarian, Japanese, Korean, Portuguese, and Vietnamese), and report on the results of a shared task challenge which attracted 20 teams to solve the task. In our meta-analysis, we focus on three aspects of the resulting systems: external training corpus selection, model architecture and training decisions, and decoding and filtering strategies. We find that strong systems start with a large amount of generic training data, and then fine-tune with in-domain data, sampled according to our provided learner response frequencies.</abstract>
<identifier type="citekey">mayhew-etal-2020-simultaneous</identifier>
<identifier type="doi">10.18653/v1/2020.ngt-1.28</identifier>
<location>
<url>https://aclanthology.org/2020.ngt-1.28</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>232</start>
<end>243</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simultaneous Translation and Paraphrase for Language Education
%A Mayhew, Stephen
%A Bicknell, Klinton
%A Brust, Chris
%A McDowell, Bill
%A Monroe, Will
%A Settles, Burr
%S Proceedings of the Fourth Workshop on Neural Generation and Translation
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F mayhew-etal-2020-simultaneous
%X We present the task of Simultaneous Translation and Paraphrasing for Language Education (STAPLE). Given a prompt in one language, the goal is to generate a diverse set of correct translations that language learners are likely to produce. This is motivated by the need to create and maintain large, high-quality sets of acceptable translations for exercises in a language-learning application, and synthesizes work spanning machine translation, MT evaluation, automatic paraphrasing, and language education technology. We developed a novel corpus with unique properties for five languages (Hungarian, Japanese, Korean, Portuguese, and Vietnamese), and report on the results of a shared task challenge which attracted 20 teams to solve the task. In our meta-analysis, we focus on three aspects of the resulting systems: external training corpus selection, model architecture and training decisions, and decoding and filtering strategies. We find that strong systems start with a large amount of generic training data, and then fine-tune with in-domain data, sampled according to our provided learner response frequencies.
%R 10.18653/v1/2020.ngt-1.28
%U https://aclanthology.org/2020.ngt-1.28
%U https://doi.org/10.18653/v1/2020.ngt-1.28
%P 232-243
Markdown (Informal)
[Simultaneous Translation and Paraphrase for Language Education](https://aclanthology.org/2020.ngt-1.28) (Mayhew et al., NGT 2020)
ACL