SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1809.09600 · 2018

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

Ruslan Salakhutdinov, Yoshua Bengio, William Cohen, Christopher Manning, Peng Qi, Zhilin Yang, Saizheng Zhang

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 8 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
hotpotqa/hotpot canonical 8 of 8
FunctionStatusWhere it lives
exact_match_score Ran hotpotqa/hotpot/hotpot_evaluate_v1.py
code served (permissive licence) · get_code("9d0dc82a4491f803")
f1_score Ran hotpotqa/hotpot/hotpot_evaluate_v1.py
code served (permissive licence) · get_code("32a5f1733d9a8971")
find_nearest Ran hotpotqa/hotpot/prepro.py
code served (permissive licence) · get_code("5733fa44ca6deb1f")
fix_span Ran hotpotqa/hotpot/prepro.py
code served (permissive licence) · get_code("40e9cb6c8ca7fb3d")
get_buckets Ran hotpotqa/hotpot/util.py
code served (permissive licence) · get_code("ffc8a36cce91c106")
has_digit Ran hotpotqa/hotpot/util.py
code served (permissive licence) · get_code("2be785f92fd075df")
normalize_answer Ran hotpotqa/hotpot/hotpot_evaluate_v1.py
code served (permissive licence) · get_code("dae7ab386661a4f4")
prepro Ran hotpotqa/hotpot/util.py
code served (permissive licence) · get_code("c15e3bee3bb007b7")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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. * These authors contributed equally. The order of authorship is decided through dice rolling. † Work done when WWC was at CMU.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1809.09600")
get_code_for_paper("1809.09600")
have("1809.09600")

Connect an agent — have() is free.