Automated Crossword Solving

Eric Wallace, Nicholas Tomlin, Albert Xu, Kevin Yang, Eshaan Pathak, Matthew Ginsberg, Dan Klein


Abstract
We present the Berkeley Crossword Solver, a state-of-the-art approach for automatically solving crossword puzzles. Our system works by generating answer candidates for each crossword clue using neural question answering models and then combines loopy belief propagation with local search to find full puzzle solutions. Compared to existing approaches, our system improves exact puzzle accuracy from 57% to 82% on crosswords from The New York Times and obtains 99.9% letter accuracy on themeless puzzles. Our system also won first place at the top human crossword tournament, which marks the first time that a computer program has surpassed human performance at this event. To facilitate research on question answering and crossword solving, we analyze our system’s remaining errors and release a dataset of over six million question-answer pairs.
Anthology ID:
2022.acl-long.219
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3073–3085
Language:
URL:
https://aclanthology.org/2022.acl-long.219
DOI:
10.18653/v1/2022.acl-long.219
Bibkey:
Cite (ACL):
Eric Wallace, Nicholas Tomlin, Albert Xu, Kevin Yang, Eshaan Pathak, Matthew Ginsberg, and Dan Klein. 2022. Automated Crossword Solving. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3073–3085, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Automated Crossword Solving (Wallace et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.219.pdf
Software:
 2022.acl-long.219.software.zip
Code
 albertkx/berkeley-crossword-solver