@inproceedings{huang-etal-2023-markqa,
title = "{M}ark{QA}: A large scale {KBQA} dataset with numerical reasoning",
author = "Huang, Xiang and
Cheng, Sitao and
Bao, Yuheng and
Huang, Shanshan and
Qu, Yuzhong",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.633/",
pages = "10241--10259",
abstract = "While question answering over knowledge bases (KBQA) has shown progress in addressing factoid questions, KBQA with numerical reasoning remains relatively unexplored. In this paper, we focus on the complex numerical reasoning in KBQA, and propose a new task, NR-KBQA, which necessitates the ability to perform both multi-hop reasoning and numerical reasoning. We also design a logic form in Python format called PyQL to represent the reasoning process of numerical reasoning questions. To facilitate the development of NR-KBQA, we present a large NR-KBQA dataset called MarkQA, which is automatically constructed by a small set of seeds. Each question in MarkQA is annotated with its corresponding SPARQL query, alongside the step-by-step reasoning path in the QDMR format and PyQL program. Experimental results of some state-of-the-art QA methods performed on the MarkQA dataset show that complex numerical reasoning in KBQA faces great challenges."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2023-markqa">
<titleInfo>
<title>MarkQA: A large scale KBQA dataset with numerical reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sitao</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuheng</namePart>
<namePart type="family">Bao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shanshan</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuzhong</namePart>
<namePart type="family">Qu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While question answering over knowledge bases (KBQA) has shown progress in addressing factoid questions, KBQA with numerical reasoning remains relatively unexplored. In this paper, we focus on the complex numerical reasoning in KBQA, and propose a new task, NR-KBQA, which necessitates the ability to perform both multi-hop reasoning and numerical reasoning. We also design a logic form in Python format called PyQL to represent the reasoning process of numerical reasoning questions. To facilitate the development of NR-KBQA, we present a large NR-KBQA dataset called MarkQA, which is automatically constructed by a small set of seeds. Each question in MarkQA is annotated with its corresponding SPARQL query, alongside the step-by-step reasoning path in the QDMR format and PyQL program. Experimental results of some state-of-the-art QA methods performed on the MarkQA dataset show that complex numerical reasoning in KBQA faces great challenges.</abstract>
<identifier type="citekey">huang-etal-2023-markqa</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.633/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>10241</start>
<end>10259</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MarkQA: A large scale KBQA dataset with numerical reasoning
%A Huang, Xiang
%A Cheng, Sitao
%A Bao, Yuheng
%A Huang, Shanshan
%A Qu, Yuzhong
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F huang-etal-2023-markqa
%X While question answering over knowledge bases (KBQA) has shown progress in addressing factoid questions, KBQA with numerical reasoning remains relatively unexplored. In this paper, we focus on the complex numerical reasoning in KBQA, and propose a new task, NR-KBQA, which necessitates the ability to perform both multi-hop reasoning and numerical reasoning. We also design a logic form in Python format called PyQL to represent the reasoning process of numerical reasoning questions. To facilitate the development of NR-KBQA, we present a large NR-KBQA dataset called MarkQA, which is automatically constructed by a small set of seeds. Each question in MarkQA is annotated with its corresponding SPARQL query, alongside the step-by-step reasoning path in the QDMR format and PyQL program. Experimental results of some state-of-the-art QA methods performed on the MarkQA dataset show that complex numerical reasoning in KBQA faces great challenges.
%U https://aclanthology.org/2023.emnlp-main.633/
%P 10241-10259
Markdown (Informal)
[MarkQA: A large scale KBQA dataset with numerical reasoning](https://aclanthology.org/2023.emnlp-main.633/) (Huang et al., EMNLP 2023)
ACL
- Xiang Huang, Sitao Cheng, Yuheng Bao, Shanshan Huang, and Yuzhong Qu. 2023. MarkQA: A large scale KBQA dataset with numerical reasoning. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 10241–10259, Singapore. Association for Computational Linguistics.