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

Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W. Cohen +2 more
9/25/2018
cs.CL

Official code: hotpotqa/hotpot (608 stars, Apache-2.0, last commit 2021-04-26).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

hotpotqa/hotpotOfficial100%
Apache-2.0
60887Shell, PythonSep 25, 20185 years agoApache-2.0

Cite this paper

@article{yang2018hotpotqa,
  title  = {HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering},
  author = {Zhilin Yang and Peng Qi and Saizheng Zhang and Yoshua Bengio and William W. Cohen and Ruslan Salakhutdinov and Christopher D. Manning},
  year   = {2018},
  eprint = {1809.09600},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1809.09600}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1809.09600.svg)](https://codeofpaper.com/paper/1809.09600)

Discussion