@inproceedings{adams-etal-2017-cross,
title = "Cross-Lingual Word Embeddings for Low-Resource Language Modeling",
author = "Adams, Oliver and
Makarucha, Adam and
Neubig, Graham and
Bird, Steven and
Cohn, Trevor",
editor = "Lapata, Mirella and
Blunsom, Phil and
Koller, Alexander",
booktitle = "Proceedings of the 15th Conference of the {E}uropean Chapter of the Association for Computational Linguistics: Volume 1, Long Papers",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/E17-1088",
pages = "937--947",
abstract = "Most languages have no established writing system and minimal written records. However, textual data is essential for natural language processing, and particularly important for training language models to support speech recognition. Even in cases where text data is missing, there are some languages for which bilingual lexicons are available, since creating lexicons is a fundamental task of documentary linguistics. We investigate the use of such lexicons to improve language models when textual training data is limited to as few as a thousand sentences. The method involves learning cross-lingual word embeddings as a preliminary step in training monolingual language models. Results across a number of languages show that language models are improved by this pre-training. Application to Yongning Na, a threatened language, highlights challenges in deploying the approach in real low-resource environments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adams-etal-2017-cross">
<titleInfo>
<title>Cross-Lingual Word Embeddings for Low-Resource Language Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oliver</namePart>
<namePart type="family">Adams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Makarucha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bird</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mirella</namePart>
<namePart type="family">Lapata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phil</namePart>
<namePart type="family">Blunsom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Koller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Most languages have no established writing system and minimal written records. However, textual data is essential for natural language processing, and particularly important for training language models to support speech recognition. Even in cases where text data is missing, there are some languages for which bilingual lexicons are available, since creating lexicons is a fundamental task of documentary linguistics. We investigate the use of such lexicons to improve language models when textual training data is limited to as few as a thousand sentences. The method involves learning cross-lingual word embeddings as a preliminary step in training monolingual language models. Results across a number of languages show that language models are improved by this pre-training. Application to Yongning Na, a threatened language, highlights challenges in deploying the approach in real low-resource environments.</abstract>
<identifier type="citekey">adams-etal-2017-cross</identifier>
<location>
<url>https://aclanthology.org/E17-1088</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>937</start>
<end>947</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Lingual Word Embeddings for Low-Resource Language Modeling
%A Adams, Oliver
%A Makarucha, Adam
%A Neubig, Graham
%A Bird, Steven
%A Cohn, Trevor
%Y Lapata, Mirella
%Y Blunsom, Phil
%Y Koller, Alexander
%S Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F adams-etal-2017-cross
%X Most languages have no established writing system and minimal written records. However, textual data is essential for natural language processing, and particularly important for training language models to support speech recognition. Even in cases where text data is missing, there are some languages for which bilingual lexicons are available, since creating lexicons is a fundamental task of documentary linguistics. We investigate the use of such lexicons to improve language models when textual training data is limited to as few as a thousand sentences. The method involves learning cross-lingual word embeddings as a preliminary step in training monolingual language models. Results across a number of languages show that language models are improved by this pre-training. Application to Yongning Na, a threatened language, highlights challenges in deploying the approach in real low-resource environments.
%U https://aclanthology.org/E17-1088
%P 937-947
Markdown (Informal)
[Cross-Lingual Word Embeddings for Low-Resource Language Modeling](https://aclanthology.org/E17-1088) (Adams et al., EACL 2017)
ACL
- Oliver Adams, Adam Makarucha, Graham Neubig, Steven Bird, and Trevor Cohn. 2017. Cross-Lingual Word Embeddings for Low-Resource Language Modeling. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 937–947, Valencia, Spain. Association for Computational Linguistics.