@inproceedings{chopra-etal-2021-switch-point,
title = "Switch Point biased Self-Training: Re-purposing Pretrained Models for Code-Switching",
author = "Chopra, Parul and
Rallabandi, Sai Krishna and
Black, Alan W and
Chandu, Khyathi Raghavi",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.373",
doi = "10.18653/v1/2021.findings-emnlp.373",
pages = "4389--4397",
abstract = "Code-switching (CS), a ubiquitous phenomenon due to the ease of communication it offers in multilingual communities still remains an understudied problem in language processing. The primary reasons behind this are: (1) minimal efforts in leveraging large pretrained multilingual models, and (2) the lack of annotated data. The distinguishing case of low performance of multilingual models in CS is the intra-sentence mixing of languages leading to switch points. We first benchmark two sequence labeling tasks {--} POS and NER on 4 different language pairs with a suite of pretrained models to identify the problems and select the best performing char-BERT model among them (addressing (1)). We then propose a self training method to repurpose the existing pretrained models using a switch-point bias by leveraging unannotated data (addressing (2)). We finally demonstrate that our approach performs well on both tasks by reducing the gap between the switch point performance while retaining the overall performance on two distinct language pairs in both the tasks. We plan to release our models and the code for all our experiments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chopra-etal-2021-switch-point">
<titleInfo>
<title>Switch Point biased Self-Training: Re-purposing Pretrained Models for Code-Switching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Parul</namePart>
<namePart type="family">Chopra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Krishna</namePart>
<namePart type="family">Rallabandi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="given">W</namePart>
<namePart type="family">Black</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="given">Raghavi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Code-switching (CS), a ubiquitous phenomenon due to the ease of communication it offers in multilingual communities still remains an understudied problem in language processing. The primary reasons behind this are: (1) minimal efforts in leveraging large pretrained multilingual models, and (2) the lack of annotated data. The distinguishing case of low performance of multilingual models in CS is the intra-sentence mixing of languages leading to switch points. We first benchmark two sequence labeling tasks – POS and NER on 4 different language pairs with a suite of pretrained models to identify the problems and select the best performing char-BERT model among them (addressing (1)). We then propose a self training method to repurpose the existing pretrained models using a switch-point bias by leveraging unannotated data (addressing (2)). We finally demonstrate that our approach performs well on both tasks by reducing the gap between the switch point performance while retaining the overall performance on two distinct language pairs in both the tasks. We plan to release our models and the code for all our experiments.</abstract>
<identifier type="citekey">chopra-etal-2021-switch-point</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.373</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.373</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>4389</start>
<end>4397</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Switch Point biased Self-Training: Re-purposing Pretrained Models for Code-Switching
%A Chopra, Parul
%A Rallabandi, Sai Krishna
%A Black, Alan W.
%A Chandu, Khyathi Raghavi
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F chopra-etal-2021-switch-point
%X Code-switching (CS), a ubiquitous phenomenon due to the ease of communication it offers in multilingual communities still remains an understudied problem in language processing. The primary reasons behind this are: (1) minimal efforts in leveraging large pretrained multilingual models, and (2) the lack of annotated data. The distinguishing case of low performance of multilingual models in CS is the intra-sentence mixing of languages leading to switch points. We first benchmark two sequence labeling tasks – POS and NER on 4 different language pairs with a suite of pretrained models to identify the problems and select the best performing char-BERT model among them (addressing (1)). We then propose a self training method to repurpose the existing pretrained models using a switch-point bias by leveraging unannotated data (addressing (2)). We finally demonstrate that our approach performs well on both tasks by reducing the gap between the switch point performance while retaining the overall performance on two distinct language pairs in both the tasks. We plan to release our models and the code for all our experiments.
%R 10.18653/v1/2021.findings-emnlp.373
%U https://aclanthology.org/2021.findings-emnlp.373
%U https://doi.org/10.18653/v1/2021.findings-emnlp.373
%P 4389-4397
Markdown (Informal)
[Switch Point biased Self-Training: Re-purposing Pretrained Models for Code-Switching](https://aclanthology.org/2021.findings-emnlp.373) (Chopra et al., Findings 2021)
ACL