@inproceedings{mullick-etal-2023-intent,
title = "Intent Identification and Entity Extraction for Healthcare Queries in {I}ndic Languages",
author = "Mullick, Ankan and
Mondal, Ishani and
Ray, Sourjyadip and
R, Raghav and
Chaitanya, G and
Goyal, Pawan",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.140",
doi = "10.18653/v1/2023.findings-eacl.140",
pages = "1870--1881",
abstract = "Scarcity of data and technological limitations for resource-poor languages in developing countries like India poses a threat to the development of sophisticated NLU systems for healthcare. To assess the current status of various state-of-the-art language models in healthcare, this paper studies the problem by initially proposing two different Healthcare datasets, Indian Healthcare Query Intent-WebMD and 1mg (IHQID-WebMD and IHQID-1mg) and one real world Indian hospital query data in English and multiple Indic languages (Hindi, Bengali, Tamil, Telugu, Marathi and Gujarati) which are annotated with the query intents as well as entities. Our aim is to detect query intents and corresponding entities. We perform extensive experiments on a set of models which in various realistic settings and explore two scenarios based on the access to English data only (less costly) and access to target language data (more expensive). We analyze context specific practical relevancy through empirical analysis. The results, expressed in terms of overall F-score show that our approach is practically useful to identify intents and entities.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mullick-etal-2023-intent">
<titleInfo>
<title>Intent Identification and Entity Extraction for Healthcare Queries in Indic Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ankan</namePart>
<namePart type="family">Mullick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ishani</namePart>
<namePart type="family">Mondal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sourjyadip</namePart>
<namePart type="family">Ray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raghav</namePart>
<namePart type="family">R</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">G</namePart>
<namePart type="family">Chaitanya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pawan</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Scarcity of data and technological limitations for resource-poor languages in developing countries like India poses a threat to the development of sophisticated NLU systems for healthcare. To assess the current status of various state-of-the-art language models in healthcare, this paper studies the problem by initially proposing two different Healthcare datasets, Indian Healthcare Query Intent-WebMD and 1mg (IHQID-WebMD and IHQID-1mg) and one real world Indian hospital query data in English and multiple Indic languages (Hindi, Bengali, Tamil, Telugu, Marathi and Gujarati) which are annotated with the query intents as well as entities. Our aim is to detect query intents and corresponding entities. We perform extensive experiments on a set of models which in various realistic settings and explore two scenarios based on the access to English data only (less costly) and access to target language data (more expensive). We analyze context specific practical relevancy through empirical analysis. The results, expressed in terms of overall F-score show that our approach is practically useful to identify intents and entities.</abstract>
<identifier type="citekey">mullick-etal-2023-intent</identifier>
<identifier type="doi">10.18653/v1/2023.findings-eacl.140</identifier>
<location>
<url>https://aclanthology.org/2023.findings-eacl.140</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>1870</start>
<end>1881</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Intent Identification and Entity Extraction for Healthcare Queries in Indic Languages
%A Mullick, Ankan
%A Mondal, Ishani
%A Ray, Sourjyadip
%A R, Raghav
%A Chaitanya, G.
%A Goyal, Pawan
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F mullick-etal-2023-intent
%X Scarcity of data and technological limitations for resource-poor languages in developing countries like India poses a threat to the development of sophisticated NLU systems for healthcare. To assess the current status of various state-of-the-art language models in healthcare, this paper studies the problem by initially proposing two different Healthcare datasets, Indian Healthcare Query Intent-WebMD and 1mg (IHQID-WebMD and IHQID-1mg) and one real world Indian hospital query data in English and multiple Indic languages (Hindi, Bengali, Tamil, Telugu, Marathi and Gujarati) which are annotated with the query intents as well as entities. Our aim is to detect query intents and corresponding entities. We perform extensive experiments on a set of models which in various realistic settings and explore two scenarios based on the access to English data only (less costly) and access to target language data (more expensive). We analyze context specific practical relevancy through empirical analysis. The results, expressed in terms of overall F-score show that our approach is practically useful to identify intents and entities.
%R 10.18653/v1/2023.findings-eacl.140
%U https://aclanthology.org/2023.findings-eacl.140
%U https://doi.org/10.18653/v1/2023.findings-eacl.140
%P 1870-1881
Markdown (Informal)
[Intent Identification and Entity Extraction for Healthcare Queries in Indic Languages](https://aclanthology.org/2023.findings-eacl.140) (Mullick et al., Findings 2023)
ACL