HOTPOTQA: A Dataset for Diverse, Explainable Multi-hop Question Answering

被引：0

作者：

Yang, Zhilin ^{[1
]}

Peng, Qi ^{[2
]}

Zhang, Saizheng ^{[3
]}

Bengiov, Yoshua ^{[3
,4
]}

Cohent, William W. ^{[5
]}

Salakhutdinov, Ruslan ^{[1
]}

Manning, Christopher D. ^{[2
]}

机构：

[1] Carnegie Mellon Univ, Pittsburgh, PA 15213 USA

[2] Stanford Univ, Stanford, CA 94305 USA

[3] Univ Montreal, Mila, Montreal, PQ, Canada

[4] CIFAR, Rome, Italy

[5] Google AI, Mountain View, CA USA

来源：

2018 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2018) | 2018年

基金：

美国国家科学基金会;

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Existing question answering (QA) datasets fail to train QA systems to perform complex reasoning and provide explanations for answers. We introduce HOTPOTQA, a new dataset with 113k Wikipedia-based question-answer pairs with four key features: (1) the questions require finding and reasoning over multiple supporting documents to answer; (2) the questions are diverse and not constrained to any pre-existing knowledge bases or knowledge schemas; (3) we provide sentence-level supporting facts required for reasoning, allowing QA systems to reason with strong supervision and explain the predictions; (4) we offer a new type of factoid comparison questions to test QA systems' ability to extract relevant facts and perform necessary comparison. We show that HOTPOTQA is challenging for the latest QA systems, and the supporting facts enable models to improve performance and make explainable predictions.

引用

页码：2369 / 2380

页数：12

共 50 条

[21] PokeMQA: Programmable knowledge editing for Multi-hop Question Answering
Gu, Hengrui
Zhou, Kaixiong
Han, Xiaotian
Liu, Ninghao
Wang, Ruobing
Wang, Xin
PROCEEDINGS OF THE 62ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1: LONG PAPERS, 2024, : 8069 - 8083
[22] Modeling Multi-hop Question Answering as Single Sequence Prediction
Yavuz, Semih
Hashimoto, Kazuma
Zhou, Yingbo
Keskar, Nitish Shirish
Xiong, Caiming
PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), VOL 1: (LONG PAPERS), 2022, : 974 - 990
[23] Breadth First Reasoning Graph for Multi-hop Question Answering
Huang, Yongjie
Yang, Meng
2021 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL-HLT 2021), 2021, : 5810 - 5821
[24] Text Reasoning Chain Extraction for Multi-Hop Question Answering
Wang, Pengming
Zhu, Zijiang
Chen, Qing
Dai, Weihuang
TSINGHUA SCIENCE AND TECHNOLOGY, 2024, 29 (04): : 959 - 970
[25] Multi-view Semantic Reasoning Networks for Multi-hop Question Answering
Long X.
Zhao R.
Sun J.
Ju S.
Gongcheng Kexue Yu Jishu/Advanced Engineering Sciences, 2023, 55 (02): : 285 - 297
[26] Uncertainty Guided Global Memory Improves Multi-Hop Question Answering
Sagirova, Alsu
Burtsev, Mikhail
2023 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING, EMNLP 2023, 2023, : 4317 - 4328
[27] Multi-Hop Paragraph Retrieval for Open-Domain Question Answering
Feldman, Yair
El-Yaniv, Ran
57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), 2019, : 2296 - 2309
[28] SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoning
Atzeni, Mattia
Bogojeska, Jasmina
Loukas, Andreas
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021,
[29] Incorporating Phrases in Latent Query Reformulation for Multi-Hop Question Answering
Tang, Jiuyang
Hu, Shengze
Chen, Ziyang
Xu, Hao
Tan, Zhen
MATHEMATICS, 2022, 10 (04)
[30] Analyzing the Effectiveness of the Underlying Reasoning Tasks in Multi-hop Question Answering
Ho, Xanh
Nguyen, Anh-Khoa Duong
Sugawara, Saku
Aizawa, Akiko
17TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EACL 2023, 2023, : 1163 - 1180

← 1 2 3 4 5 →