@inproceedings{ai-fang-2022-vocabulary,
title = "Vocabulary-informed Language Encoding",
author = "Ai, Xi and
Fang, Bin",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.432",
pages = "4883--4891",
abstract = "A Multilingual model relies on language encodings to identify input languages because the multilingual model has to distinguish between the input and output languages or among all the languages for cross-lingual tasks. Furthermore, we find that language encodings potentially refine multiple morphologies of different languages to form a better isomorphic space for multilinguality. To leverage this observation, we present a method to compute a vocabulary-informed language encoding as the language representation, for a required language, considering a local vocabulary covering an acceptable amount of the most frequent word embeddings in this language. In our experiments, our method can consistently improve the performance of multilingual models on unsupervised neural machine translation and cross-lingual embedding.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ai-fang-2022-vocabulary">
<titleInfo>
<title>Vocabulary-informed Language Encoding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Ai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A Multilingual model relies on language encodings to identify input languages because the multilingual model has to distinguish between the input and output languages or among all the languages for cross-lingual tasks. Furthermore, we find that language encodings potentially refine multiple morphologies of different languages to form a better isomorphic space for multilinguality. To leverage this observation, we present a method to compute a vocabulary-informed language encoding as the language representation, for a required language, considering a local vocabulary covering an acceptable amount of the most frequent word embeddings in this language. In our experiments, our method can consistently improve the performance of multilingual models on unsupervised neural machine translation and cross-lingual embedding.</abstract>
<identifier type="citekey">ai-fang-2022-vocabulary</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.432</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>4883</start>
<end>4891</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Vocabulary-informed Language Encoding
%A Ai, Xi
%A Fang, Bin
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F ai-fang-2022-vocabulary
%X A Multilingual model relies on language encodings to identify input languages because the multilingual model has to distinguish between the input and output languages or among all the languages for cross-lingual tasks. Furthermore, we find that language encodings potentially refine multiple morphologies of different languages to form a better isomorphic space for multilinguality. To leverage this observation, we present a method to compute a vocabulary-informed language encoding as the language representation, for a required language, considering a local vocabulary covering an acceptable amount of the most frequent word embeddings in this language. In our experiments, our method can consistently improve the performance of multilingual models on unsupervised neural machine translation and cross-lingual embedding.
%U https://aclanthology.org/2022.coling-1.432
%P 4883-4891
Markdown (Informal)
[Vocabulary-informed Language Encoding](https://aclanthology.org/2022.coling-1.432) (Ai & Fang, COLING 2022)
ACL
- Xi Ai and Bin Fang. 2022. Vocabulary-informed Language Encoding. In Proceedings of the 29th International Conference on Computational Linguistics, pages 4883–4891, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.