@inproceedings{wang-etal-2021-multi-view,
title = "Multi-view Subword Regularization",
author = "Wang, Xinyi and
Ruder, Sebastian and
Neubig, Graham",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.40/",
doi = "10.18653/v1/2021.naacl-main.40",
pages = "473--482",
abstract = "Multilingual pretrained representations generally rely on subword segmentation algorithms to create a shared multilingual vocabulary. However, standard heuristic algorithms often lead to sub-optimal segmentation, especially for languages with limited amounts of data. In this paper, we take two major steps towards alleviating this problem. First, we demonstrate empirically that applying existing subword regularization methods (Kudo, 2018; Provilkov et al., 2020) during fine-tuning of pre-trained multilingual representations improves the effectiveness of cross-lingual transfer. Second, to take full advantage of different possible input segmentations, we propose Multi-view Subword Regularization (MVR), a method that enforces the consistency of predictors between using inputs tokenized by the standard and probabilistic segmentations. Results on the XTREME multilingual benchmark (Hu et al., 2020) show that MVR brings consistent improvements of up to 2.5 points over using standard segmentation algorithms."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2021-multi-view">
<titleInfo>
<title>Multi-view Subword Regularization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xinyi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Ruder</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>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</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>Multilingual pretrained representations generally rely on subword segmentation algorithms to create a shared multilingual vocabulary. However, standard heuristic algorithms often lead to sub-optimal segmentation, especially for languages with limited amounts of data. In this paper, we take two major steps towards alleviating this problem. First, we demonstrate empirically that applying existing subword regularization methods (Kudo, 2018; Provilkov et al., 2020) during fine-tuning of pre-trained multilingual representations improves the effectiveness of cross-lingual transfer. Second, to take full advantage of different possible input segmentations, we propose Multi-view Subword Regularization (MVR), a method that enforces the consistency of predictors between using inputs tokenized by the standard and probabilistic segmentations. Results on the XTREME multilingual benchmark (Hu et al., 2020) show that MVR brings consistent improvements of up to 2.5 points over using standard segmentation algorithms.</abstract>
<identifier type="citekey">wang-etal-2021-multi-view</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.40</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.40/</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>473</start>
<end>482</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-view Subword Regularization
%A Wang, Xinyi
%A Ruder, Sebastian
%A Neubig, Graham
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F wang-etal-2021-multi-view
%X Multilingual pretrained representations generally rely on subword segmentation algorithms to create a shared multilingual vocabulary. However, standard heuristic algorithms often lead to sub-optimal segmentation, especially for languages with limited amounts of data. In this paper, we take two major steps towards alleviating this problem. First, we demonstrate empirically that applying existing subword regularization methods (Kudo, 2018; Provilkov et al., 2020) during fine-tuning of pre-trained multilingual representations improves the effectiveness of cross-lingual transfer. Second, to take full advantage of different possible input segmentations, we propose Multi-view Subword Regularization (MVR), a method that enforces the consistency of predictors between using inputs tokenized by the standard and probabilistic segmentations. Results on the XTREME multilingual benchmark (Hu et al., 2020) show that MVR brings consistent improvements of up to 2.5 points over using standard segmentation algorithms.
%R 10.18653/v1/2021.naacl-main.40
%U https://aclanthology.org/2021.naacl-main.40/
%U https://doi.org/10.18653/v1/2021.naacl-main.40
%P 473-482
Markdown (Informal)
[Multi-view Subword Regularization](https://aclanthology.org/2021.naacl-main.40/) (Wang et al., NAACL 2021)
ACL
- Xinyi Wang, Sebastian Ruder, and Graham Neubig. 2021. Multi-view Subword Regularization. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 473–482, Online. Association for Computational Linguistics.