@inproceedings{lakew-etal-2017-improving,
title = "Improving Zero-Shot Translation of Low-Resource Languages",
author = "Lakew, Surafel M. and
Lotito, Quintino F. and
Negri, Matteo and
Turchi, Marco and
Federico, Marcello",
editor = "Sakti, Sakriani and
Utiyama, Masao",
booktitle = "Proceedings of the 14th International Conference on Spoken Language Translation",
month = dec # " 14-15",
year = "2017",
address = "Tokyo, Japan",
publisher = "International Workshop on Spoken Language Translation",
url = "https://aclanthology.org/2017.iwslt-1.16",
pages = "113--119",
abstract = "Recent work on multilingual neural machine translation reported competitive performance with respect to bilingual models and surprisingly good performance even on (zero-shot) translation directions not observed at training time. We investigate here a zero-shot translation in a particularly low-resource multilingual setting. We propose a simple iterative training procedure that leverages a duality of translations directly generated by the system for the zero-shot directions. The translations produced by the system (sub-optimal since they contain mixed language from the shared vocabulary), are then used together with the original parallel data to feed and iteratively re-train the multilingual network. Over time, this allows the system to learn from its own generated and increasingly better output. Our approach shows to be effective in improving the two zero-shot directions of our multilingual model. In particular, we observed gains of about 9 BLEU points over a baseline multilingual model and up to 2.08 BLEU over a pivoting mechanism using two bilingual models. Further analysis shows that there is also a slight improvement in the non-zero-shot language directions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lakew-etal-2017-improving">
<titleInfo>
<title>Improving Zero-Shot Translation of Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Surafel</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Lakew</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quintino</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Lotito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-dec 14-15</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Conference on Spoken Language Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Workshop on Spoken Language Translation</publisher>
<place>
<placeTerm type="text">Tokyo, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent work on multilingual neural machine translation reported competitive performance with respect to bilingual models and surprisingly good performance even on (zero-shot) translation directions not observed at training time. We investigate here a zero-shot translation in a particularly low-resource multilingual setting. We propose a simple iterative training procedure that leverages a duality of translations directly generated by the system for the zero-shot directions. The translations produced by the system (sub-optimal since they contain mixed language from the shared vocabulary), are then used together with the original parallel data to feed and iteratively re-train the multilingual network. Over time, this allows the system to learn from its own generated and increasingly better output. Our approach shows to be effective in improving the two zero-shot directions of our multilingual model. In particular, we observed gains of about 9 BLEU points over a baseline multilingual model and up to 2.08 BLEU over a pivoting mechanism using two bilingual models. Further analysis shows that there is also a slight improvement in the non-zero-shot language directions.</abstract>
<identifier type="citekey">lakew-etal-2017-improving</identifier>
<location>
<url>https://aclanthology.org/2017.iwslt-1.16</url>
</location>
<part>
<date>2017-dec 14-15</date>
<extent unit="page">
<start>113</start>
<end>119</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Zero-Shot Translation of Low-Resource Languages
%A Lakew, Surafel M.
%A Lotito, Quintino F.
%A Negri, Matteo
%A Turchi, Marco
%A Federico, Marcello
%Y Sakti, Sakriani
%Y Utiyama, Masao
%S Proceedings of the 14th International Conference on Spoken Language Translation
%D 2017
%8 dec 14 15
%I International Workshop on Spoken Language Translation
%C Tokyo, Japan
%F lakew-etal-2017-improving
%X Recent work on multilingual neural machine translation reported competitive performance with respect to bilingual models and surprisingly good performance even on (zero-shot) translation directions not observed at training time. We investigate here a zero-shot translation in a particularly low-resource multilingual setting. We propose a simple iterative training procedure that leverages a duality of translations directly generated by the system for the zero-shot directions. The translations produced by the system (sub-optimal since they contain mixed language from the shared vocabulary), are then used together with the original parallel data to feed and iteratively re-train the multilingual network. Over time, this allows the system to learn from its own generated and increasingly better output. Our approach shows to be effective in improving the two zero-shot directions of our multilingual model. In particular, we observed gains of about 9 BLEU points over a baseline multilingual model and up to 2.08 BLEU over a pivoting mechanism using two bilingual models. Further analysis shows that there is also a slight improvement in the non-zero-shot language directions.
%U https://aclanthology.org/2017.iwslt-1.16
%P 113-119
Markdown (Informal)
[Improving Zero-Shot Translation of Low-Resource Languages](https://aclanthology.org/2017.iwslt-1.16) (Lakew et al., IWSLT 2017)
ACL
- Surafel M. Lakew, Quintino F. Lotito, Matteo Negri, Marco Turchi, and Marcello Federico. 2017. Improving Zero-Shot Translation of Low-Resource Languages. In Proceedings of the 14th International Conference on Spoken Language Translation, pages 113–119, Tokyo, Japan. International Workshop on Spoken Language Translation.