@inproceedings{choshen-abend-2019-automatically,
title = "Automatically Extracting Challenge Sets for Non-Local Phenomena in Neural Machine Translation",
author = "Choshen, Leshem and
Abend, Omri",
editor = "Bansal, Mohit and
Villavicencio, Aline",
booktitle = "Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/K19-1028",
doi = "10.18653/v1/K19-1028",
pages = "291--303",
abstract = "We show that the state-of-the-art Transformer MT model is not biased towards monotonic reordering (unlike previous recurrent neural network models), but that nevertheless, long-distance dependencies remain a challenge for the model. Since most dependencies are short-distance, common evaluation metrics will be little influenced by how well systems perform on them. We therefore propose an automatic approach for extracting challenge sets rich with long-distance dependencies, and argue that evaluation using this methodology provides a complementary perspective on system performance. To support our claim, we compile challenge sets for English-German and German-English, which are much larger than any previously released challenge set for MT. The extracted sets are large enough to allow reliable automatic evaluation, which makes the proposed approach a scalable and practical solution for evaluating MT performance on the long-tail of syntactic phenomena.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="choshen-abend-2019-automatically">
<titleInfo>
<title>Automatically Extracting Challenge Sets for Non-Local Phenomena in Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leshem</namePart>
<namePart type="family">Choshen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omri</namePart>
<namePart type="family">Abend</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 23rd Conference on Computational Natural Language Learning (CoNLL)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</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>We show that the state-of-the-art Transformer MT model is not biased towards monotonic reordering (unlike previous recurrent neural network models), but that nevertheless, long-distance dependencies remain a challenge for the model. Since most dependencies are short-distance, common evaluation metrics will be little influenced by how well systems perform on them. We therefore propose an automatic approach for extracting challenge sets rich with long-distance dependencies, and argue that evaluation using this methodology provides a complementary perspective on system performance. To support our claim, we compile challenge sets for English-German and German-English, which are much larger than any previously released challenge set for MT. The extracted sets are large enough to allow reliable automatic evaluation, which makes the proposed approach a scalable and practical solution for evaluating MT performance on the long-tail of syntactic phenomena.</abstract>
<identifier type="citekey">choshen-abend-2019-automatically</identifier>
<identifier type="doi">10.18653/v1/K19-1028</identifier>
<location>
<url>https://aclanthology.org/K19-1028</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>291</start>
<end>303</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatically Extracting Challenge Sets for Non-Local Phenomena in Neural Machine Translation
%A Choshen, Leshem
%A Abend, Omri
%Y Bansal, Mohit
%Y Villavicencio, Aline
%S Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F choshen-abend-2019-automatically
%X We show that the state-of-the-art Transformer MT model is not biased towards monotonic reordering (unlike previous recurrent neural network models), but that nevertheless, long-distance dependencies remain a challenge for the model. Since most dependencies are short-distance, common evaluation metrics will be little influenced by how well systems perform on them. We therefore propose an automatic approach for extracting challenge sets rich with long-distance dependencies, and argue that evaluation using this methodology provides a complementary perspective on system performance. To support our claim, we compile challenge sets for English-German and German-English, which are much larger than any previously released challenge set for MT. The extracted sets are large enough to allow reliable automatic evaluation, which makes the proposed approach a scalable and practical solution for evaluating MT performance on the long-tail of syntactic phenomena.
%R 10.18653/v1/K19-1028
%U https://aclanthology.org/K19-1028
%U https://doi.org/10.18653/v1/K19-1028
%P 291-303
Markdown (Informal)
[Automatically Extracting Challenge Sets for Non-Local Phenomena in Neural Machine Translation](https://aclanthology.org/K19-1028) (Choshen & Abend, CoNLL 2019)
ACL