@inproceedings{otani-etal-2020-pre,
title = "Pre-tokenization of Multi-word Expressions in Cross-lingual Word Embeddings",
author = "Otani, Naoki and
Ozaki, Satoru and
Zhao, Xingyuan and
Li, Yucen and
St Johns, Micaelah and
Levin, Lori",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.360",
doi = "10.18653/v1/2020.emnlp-main.360",
pages = "4451--4464",
abstract = "Cross-lingual word embedding (CWE) algorithms represent words in multiple languages in a unified vector space. Multi-Word Expressions (MWE) are common in every language. When training word embeddings, each component word of an MWE gets its own separate embedding, and thus, MWEs are not translated by CWEs. We propose a simple method for word translation of MWEs to and from English in ten languages: we first compile lists of MWEs in each language and then tokenize the MWEs as single tokens before training word embeddings. CWEs are trained on a word-translation task using the dictionaries that only contain single words. In order to evaluate MWE translation, we created bilingual word lists from multilingual WordNet that include single-token words and MWEs, and most importantly, include MWEs that correspond to single words in another language. We release these dictionaries to the research community. We show that the pre-tokenization of MWEs as single tokens performs better than averaging the embeddings of the individual tokens of the MWE. We can translate MWEs at a top-10 precision of 30-60{\%}. The tokenization of MWEs makes the occurrences of single words in a training corpus more sparse, but we show that it does not pose negative impacts on single-word translations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="otani-etal-2020-pre">
<titleInfo>
<title>Pre-tokenization of Multi-word Expressions in Cross-lingual Word Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Naoki</namePart>
<namePart type="family">Otani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satoru</namePart>
<namePart type="family">Ozaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingyuan</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yucen</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Micaelah</namePart>
<namePart type="family">St Johns</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lori</namePart>
<namePart type="family">Levin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cross-lingual word embedding (CWE) algorithms represent words in multiple languages in a unified vector space. Multi-Word Expressions (MWE) are common in every language. When training word embeddings, each component word of an MWE gets its own separate embedding, and thus, MWEs are not translated by CWEs. We propose a simple method for word translation of MWEs to and from English in ten languages: we first compile lists of MWEs in each language and then tokenize the MWEs as single tokens before training word embeddings. CWEs are trained on a word-translation task using the dictionaries that only contain single words. In order to evaluate MWE translation, we created bilingual word lists from multilingual WordNet that include single-token words and MWEs, and most importantly, include MWEs that correspond to single words in another language. We release these dictionaries to the research community. We show that the pre-tokenization of MWEs as single tokens performs better than averaging the embeddings of the individual tokens of the MWE. We can translate MWEs at a top-10 precision of 30-60%. The tokenization of MWEs makes the occurrences of single words in a training corpus more sparse, but we show that it does not pose negative impacts on single-word translations.</abstract>
<identifier type="citekey">otani-etal-2020-pre</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.360</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.360</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>4451</start>
<end>4464</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pre-tokenization of Multi-word Expressions in Cross-lingual Word Embeddings
%A Otani, Naoki
%A Ozaki, Satoru
%A Zhao, Xingyuan
%A Li, Yucen
%A St Johns, Micaelah
%A Levin, Lori
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F otani-etal-2020-pre
%X Cross-lingual word embedding (CWE) algorithms represent words in multiple languages in a unified vector space. Multi-Word Expressions (MWE) are common in every language. When training word embeddings, each component word of an MWE gets its own separate embedding, and thus, MWEs are not translated by CWEs. We propose a simple method for word translation of MWEs to and from English in ten languages: we first compile lists of MWEs in each language and then tokenize the MWEs as single tokens before training word embeddings. CWEs are trained on a word-translation task using the dictionaries that only contain single words. In order to evaluate MWE translation, we created bilingual word lists from multilingual WordNet that include single-token words and MWEs, and most importantly, include MWEs that correspond to single words in another language. We release these dictionaries to the research community. We show that the pre-tokenization of MWEs as single tokens performs better than averaging the embeddings of the individual tokens of the MWE. We can translate MWEs at a top-10 precision of 30-60%. The tokenization of MWEs makes the occurrences of single words in a training corpus more sparse, but we show that it does not pose negative impacts on single-word translations.
%R 10.18653/v1/2020.emnlp-main.360
%U https://aclanthology.org/2020.emnlp-main.360
%U https://doi.org/10.18653/v1/2020.emnlp-main.360
%P 4451-4464
Markdown (Informal)
[Pre-tokenization of Multi-word Expressions in Cross-lingual Word Embeddings](https://aclanthology.org/2020.emnlp-main.360) (Otani et al., EMNLP 2020)
ACL