@inproceedings{nag-etal-2021-data,
title = "A Data Bootstrapping Recipe for Low-Resource Multilingual Relation Classification",
author = "Nag, Arijit and
Samanta, Bidisha and
Mukherjee, Animesh and
Ganguly, Niloy and
Chakrabarti, Soumen",
editor = "Bisazza, Arianna and
Abend, Omri",
booktitle = "Proceedings of the 25th Conference on Computational Natural Language Learning",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.conll-1.45",
doi = "10.18653/v1/2021.conll-1.45",
pages = "575--587",
abstract = "Relation classification (sometimes called {`}extraction{'}) requires trustworthy datasets for fine-tuning large language models, as well as for evaluation. Data collection is challenging for Indian languages, because they are syntactically and morphologically diverse, as well as different from resource-rich languages like English. Despite recent interest in deep generative models for Indian languages, relation classification is still not well-served by public data sets. In response, we present IndoRE, a dataset with 39K entity- and relation-tagged gold sentences in three Indian languages, plus English. We start with a multilingual BERT (mBERT) based system that captures entity span positions and type information and provides competitive monolingual relation classification. Using this system, we explore and compare transfer mechanisms between languages. In particular, we study the accuracy-efficiency tradeoff between expensive gold instances vs. translated and aligned {`}silver{'} instances.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nag-etal-2021-data">
<titleInfo>
<title>A Data Bootstrapping Recipe for Low-Resource Multilingual Relation Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arijit</namePart>
<namePart type="family">Nag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bidisha</namePart>
<namePart type="family">Samanta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Animesh</namePart>
<namePart type="family">Mukherjee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niloy</namePart>
<namePart type="family">Ganguly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soumen</namePart>
<namePart type="family">Chakrabarti</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>Proceedings of the 25th Conference on Computational Natural Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arianna</namePart>
<namePart type="family">Bisazza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omri</namePart>
<namePart type="family">Abend</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>Relation classification (sometimes called ‘extraction’) requires trustworthy datasets for fine-tuning large language models, as well as for evaluation. Data collection is challenging for Indian languages, because they are syntactically and morphologically diverse, as well as different from resource-rich languages like English. Despite recent interest in deep generative models for Indian languages, relation classification is still not well-served by public data sets. In response, we present IndoRE, a dataset with 39K entity- and relation-tagged gold sentences in three Indian languages, plus English. We start with a multilingual BERT (mBERT) based system that captures entity span positions and type information and provides competitive monolingual relation classification. Using this system, we explore and compare transfer mechanisms between languages. In particular, we study the accuracy-efficiency tradeoff between expensive gold instances vs. translated and aligned ‘silver’ instances.</abstract>
<identifier type="citekey">nag-etal-2021-data</identifier>
<identifier type="doi">10.18653/v1/2021.conll-1.45</identifier>
<location>
<url>https://aclanthology.org/2021.conll-1.45</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>575</start>
<end>587</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Data Bootstrapping Recipe for Low-Resource Multilingual Relation Classification
%A Nag, Arijit
%A Samanta, Bidisha
%A Mukherjee, Animesh
%A Ganguly, Niloy
%A Chakrabarti, Soumen
%Y Bisazza, Arianna
%Y Abend, Omri
%S Proceedings of the 25th Conference on Computational Natural Language Learning
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online
%F nag-etal-2021-data
%X Relation classification (sometimes called ‘extraction’) requires trustworthy datasets for fine-tuning large language models, as well as for evaluation. Data collection is challenging for Indian languages, because they are syntactically and morphologically diverse, as well as different from resource-rich languages like English. Despite recent interest in deep generative models for Indian languages, relation classification is still not well-served by public data sets. In response, we present IndoRE, a dataset with 39K entity- and relation-tagged gold sentences in three Indian languages, plus English. We start with a multilingual BERT (mBERT) based system that captures entity span positions and type information and provides competitive monolingual relation classification. Using this system, we explore and compare transfer mechanisms between languages. In particular, we study the accuracy-efficiency tradeoff between expensive gold instances vs. translated and aligned ‘silver’ instances.
%R 10.18653/v1/2021.conll-1.45
%U https://aclanthology.org/2021.conll-1.45
%U https://doi.org/10.18653/v1/2021.conll-1.45
%P 575-587
Markdown (Informal)
[A Data Bootstrapping Recipe for Low-Resource Multilingual Relation Classification](https://aclanthology.org/2021.conll-1.45) (Nag et al., CoNLL 2021)
ACL