@inproceedings{singh-etal-2022-massively,
title = "Massively Multilingual Language Models for Cross Lingual Fact Extraction from Low Resource {I}ndian Languages",
author = "Singh, Bhavyajeet and
Kandru, Siri Venkata Pavan Kumar and
Sharma, Anubhav and
Varma, Vasudeva",
editor = "Akhtar, Md. Shad and
Chakraborty, Tanmoy",
booktitle = "Proceedings of the 19th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2022",
address = "New Delhi, India",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.icon-main.2",
pages = "11--18",
abstract = "Massive knowledge graphs like Wikidata attempt to capture world knowledge about multiple entities. Recent approaches concentrate on automatically enriching these KGs from text. However a lot of information present in the form of natural text in low resource languages is often missed out. Cross Lingual Information Extraction aims at extracting factual information in the form of English triples from low resource Indian Language text. Despite its massive potential, progress made on this task is lagging when compared to Monolingual Information Extraction. In this paper, we propose the task of Cross Lingual Fact Extraction(CLFE) from text and devise an end-to-end generative approach for the same which achieves an overall F1 score of 77.46",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-etal-2022-massively">
<titleInfo>
<title>Massively Multilingual Language Models for Cross Lingual Fact Extraction from Low Resource Indian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bhavyajeet</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siri</namePart>
<namePart type="given">Venkata</namePart>
<namePart type="given">Pavan</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Kandru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anubhav</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasudeva</namePart>
<namePart type="family">Varma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Shad</namePart>
<namePart type="family">Akhtar</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">New Delhi, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Massive knowledge graphs like Wikidata attempt to capture world knowledge about multiple entities. Recent approaches concentrate on automatically enriching these KGs from text. However a lot of information present in the form of natural text in low resource languages is often missed out. Cross Lingual Information Extraction aims at extracting factual information in the form of English triples from low resource Indian Language text. Despite its massive potential, progress made on this task is lagging when compared to Monolingual Information Extraction. In this paper, we propose the task of Cross Lingual Fact Extraction(CLFE) from text and devise an end-to-end generative approach for the same which achieves an overall F1 score of 77.46</abstract>
<identifier type="citekey">singh-etal-2022-massively</identifier>
<location>
<url>https://aclanthology.org/2022.icon-main.2</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>11</start>
<end>18</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Massively Multilingual Language Models for Cross Lingual Fact Extraction from Low Resource Indian Languages
%A Singh, Bhavyajeet
%A Kandru, Siri Venkata Pavan Kumar
%A Sharma, Anubhav
%A Varma, Vasudeva
%Y Akhtar, Md. Shad
%Y Chakraborty, Tanmoy
%S Proceedings of the 19th International Conference on Natural Language Processing (ICON)
%D 2022
%8 December
%I Association for Computational Linguistics
%C New Delhi, India
%F singh-etal-2022-massively
%X Massive knowledge graphs like Wikidata attempt to capture world knowledge about multiple entities. Recent approaches concentrate on automatically enriching these KGs from text. However a lot of information present in the form of natural text in low resource languages is often missed out. Cross Lingual Information Extraction aims at extracting factual information in the form of English triples from low resource Indian Language text. Despite its massive potential, progress made on this task is lagging when compared to Monolingual Information Extraction. In this paper, we propose the task of Cross Lingual Fact Extraction(CLFE) from text and devise an end-to-end generative approach for the same which achieves an overall F1 score of 77.46
%U https://aclanthology.org/2022.icon-main.2
%P 11-18
Markdown (Informal)
[Massively Multilingual Language Models for Cross Lingual Fact Extraction from Low Resource Indian Languages](https://aclanthology.org/2022.icon-main.2) (Singh et al., ICON 2022)
ACL