@inproceedings{nandy-etal-2021-question-answering,
title = "Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based {QA} Framework",
author = "Nandy, Abhilash and
Sharma, Soumya and
Maddhashiya, Shubham and
Sachdeva, Kapil and
Goyal, Pawan and
Ganguly, NIloy",
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.392",
doi = "10.18653/v1/2021.findings-emnlp.392",
pages = "4600--4609",
abstract = "Answering questions asked from instructional corpora such as E-manuals, recipe books, etc., has been far less studied than open-domain factoid context-based question answering. This can be primarily attributed to the absence of standard benchmark datasets. In this paper, we meticulously create a large amount of data connected with E-manuals and develop a suitable algorithm to exploit it. We collect E-Manual Corpus, a huge corpus of 307,957 E-manuals, and pretrain RoBERTa on this large corpus. We create various benchmark QA datasets which include question answer pairs curated by experts based upon two E-manuals, real user questions from Community Question Answering Forum pertaining to E-manuals etc. We introduce EMQAP (E-Manual Question Answering Pipeline) that answers questions pertaining to electronics devices. Built upon the pretrained RoBERTa, it harbors a supervised multi-task learning framework which efficiently performs the dual tasks of identifying the section in the E-manual where the answer can be found and the exact answer span within that section. For E-Manual annotated question-answer pairs, we show an improvement of about 40{\%} in ROUGE-L F1 scores over most competitive baseline. We perform a detailed ablation study and establish the versatility of EMQAP across different circumstances. The code and datasets are shared at \url{https://github.com/abhi1nandy2/EMNLP-2021-Findings}, and the corresponding project website is \url{https://sites.google.com/view/emanualqa/home}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nandy-etal-2021-question-answering">
<titleInfo>
<title>Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhilash</namePart>
<namePart type="family">Nandy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soumya</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shubham</namePart>
<namePart type="family">Maddhashiya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kapil</namePart>
<namePart type="family">Sachdeva</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>
<name type="personal">
<namePart type="given">NIloy</namePart>
<namePart type="family">Ganguly</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>Answering questions asked from instructional corpora such as E-manuals, recipe books, etc., has been far less studied than open-domain factoid context-based question answering. This can be primarily attributed to the absence of standard benchmark datasets. In this paper, we meticulously create a large amount of data connected with E-manuals and develop a suitable algorithm to exploit it. We collect E-Manual Corpus, a huge corpus of 307,957 E-manuals, and pretrain RoBERTa on this large corpus. We create various benchmark QA datasets which include question answer pairs curated by experts based upon two E-manuals, real user questions from Community Question Answering Forum pertaining to E-manuals etc. We introduce EMQAP (E-Manual Question Answering Pipeline) that answers questions pertaining to electronics devices. Built upon the pretrained RoBERTa, it harbors a supervised multi-task learning framework which efficiently performs the dual tasks of identifying the section in the E-manual where the answer can be found and the exact answer span within that section. For E-Manual annotated question-answer pairs, we show an improvement of about 40% in ROUGE-L F1 scores over most competitive baseline. We perform a detailed ablation study and establish the versatility of EMQAP across different circumstances. The code and datasets are shared at https://github.com/abhi1nandy2/EMNLP-2021-Findings, and the corresponding project website is https://sites.google.com/view/emanualqa/home.</abstract>
<identifier type="citekey">nandy-etal-2021-question-answering</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.392</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.392</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>4600</start>
<end>4609</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework
%A Nandy, Abhilash
%A Sharma, Soumya
%A Maddhashiya, Shubham
%A Sachdeva, Kapil
%A Goyal, Pawan
%A Ganguly, NIloy
%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 nandy-etal-2021-question-answering
%X Answering questions asked from instructional corpora such as E-manuals, recipe books, etc., has been far less studied than open-domain factoid context-based question answering. This can be primarily attributed to the absence of standard benchmark datasets. In this paper, we meticulously create a large amount of data connected with E-manuals and develop a suitable algorithm to exploit it. We collect E-Manual Corpus, a huge corpus of 307,957 E-manuals, and pretrain RoBERTa on this large corpus. We create various benchmark QA datasets which include question answer pairs curated by experts based upon two E-manuals, real user questions from Community Question Answering Forum pertaining to E-manuals etc. We introduce EMQAP (E-Manual Question Answering Pipeline) that answers questions pertaining to electronics devices. Built upon the pretrained RoBERTa, it harbors a supervised multi-task learning framework which efficiently performs the dual tasks of identifying the section in the E-manual where the answer can be found and the exact answer span within that section. For E-Manual annotated question-answer pairs, we show an improvement of about 40% in ROUGE-L F1 scores over most competitive baseline. We perform a detailed ablation study and establish the versatility of EMQAP across different circumstances. The code and datasets are shared at https://github.com/abhi1nandy2/EMNLP-2021-Findings, and the corresponding project website is https://sites.google.com/view/emanualqa/home.
%R 10.18653/v1/2021.findings-emnlp.392
%U https://aclanthology.org/2021.findings-emnlp.392
%U https://doi.org/10.18653/v1/2021.findings-emnlp.392
%P 4600-4609
Markdown (Informal)
[Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework](https://aclanthology.org/2021.findings-emnlp.392) (Nandy et al., Findings 2021)
ACL