@inproceedings{wang-etal-2022-new,
title = "A New Concept of Knowledge based Question Answering ({KBQA}) System for Multi-hop Reasoning",
author = "Wang, Yu and
V.srinivasan@samsung.com, V.srinivasan@samsung.com and
Jin, Hongxia",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.294",
doi = "10.18653/v1/2022.naacl-main.294",
pages = "4007--4017",
abstract = "Knowledge based question answering (KBQA) is a complex task for natural language understanding. Many KBQA approaches have been proposed in recent years, and most of them are trained based on labeled reasoning path. This hinders the system{'}s performance as many correct reasoning paths are not labeled as ground truth, and thus they cannot be learned. In this paper, we introduce a new concept of KBQA system which can leverage multiple reasoning paths{'} information and only requires labeled answer as supervision. We name it as \textbf{M}utliple \textbf{R}easoning \textbf{P}aths KB\textbf{QA} System (MRP-QA). We conduct experiments on several benchmark datasets containing both single-hop simple questions as well as muti-hop complex questions, including WebQuestionSP (WQSP), ComplexWebQuestion-1.1 (CWQ), and PathQuestion-Large (PQL), and demonstrate strong performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-new">
<titleInfo>
<title>A New Concept of Knowledge based Question Answering (KBQA) System for Multi-hop Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">V.srinivasan@samsung.com</namePart>
<namePart type="family">V.srinivasan@samsung.com</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongxia</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Knowledge based question answering (KBQA) is a complex task for natural language understanding. Many KBQA approaches have been proposed in recent years, and most of them are trained based on labeled reasoning path. This hinders the system’s performance as many correct reasoning paths are not labeled as ground truth, and thus they cannot be learned. In this paper, we introduce a new concept of KBQA system which can leverage multiple reasoning paths’ information and only requires labeled answer as supervision. We name it as Mutliple Reasoning Paths KBQA System (MRP-QA). We conduct experiments on several benchmark datasets containing both single-hop simple questions as well as muti-hop complex questions, including WebQuestionSP (WQSP), ComplexWebQuestion-1.1 (CWQ), and PathQuestion-Large (PQL), and demonstrate strong performance.</abstract>
<identifier type="citekey">wang-etal-2022-new</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.294</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.294</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>4007</start>
<end>4017</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A New Concept of Knowledge based Question Answering (KBQA) System for Multi-hop Reasoning
%A Wang, Yu
%A V.srinivasan@samsung.com, V.srinivasan@samsung.com
%A Jin, Hongxia
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F wang-etal-2022-new
%X Knowledge based question answering (KBQA) is a complex task for natural language understanding. Many KBQA approaches have been proposed in recent years, and most of them are trained based on labeled reasoning path. This hinders the system’s performance as many correct reasoning paths are not labeled as ground truth, and thus they cannot be learned. In this paper, we introduce a new concept of KBQA system which can leverage multiple reasoning paths’ information and only requires labeled answer as supervision. We name it as Mutliple Reasoning Paths KBQA System (MRP-QA). We conduct experiments on several benchmark datasets containing both single-hop simple questions as well as muti-hop complex questions, including WebQuestionSP (WQSP), ComplexWebQuestion-1.1 (CWQ), and PathQuestion-Large (PQL), and demonstrate strong performance.
%R 10.18653/v1/2022.naacl-main.294
%U https://aclanthology.org/2022.naacl-main.294
%U https://doi.org/10.18653/v1/2022.naacl-main.294
%P 4007-4017
Markdown (Informal)
[A New Concept of Knowledge based Question Answering (KBQA) System for Multi-hop Reasoning](https://aclanthology.org/2022.naacl-main.294) (Wang et al., NAACL 2022)
ACL