Automated Crossword Solving

05/19/2022
by   Eric Wallace, et al.
17

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 99.9 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.

READ FULL TEXT

page 1

page 6

page 8

page 13

research
03/23/2023

DBLP-QuAD: A Question Answering Dataset over the DBLP Scholarly Knowledge Graph

In this work we create a question answering dataset over the DBLP schola...
research
09/23/2021

BiRdQA: A Bilingual Dataset for Question Answering on Tricky Riddles

A riddle is a question or statement with double or veiled meanings, foll...
research
11/12/2016

Training IBM Watson using Automatically Generated Question-Answer Pairs

IBM Watson is a cognitive computing system capable of question answering...
research
09/24/2018

Stochastic Answer Networks for SQuAD 2.0

This paper presents an extension of the Stochastic Answer Network (SAN),...
research
09/17/2022

Learning to Answer Semantic Queries over Code

During software development, developers need answers to queries about se...
research
05/20/2022

Down and Across: Introducing Crossword-Solving as a New NLP Benchmark

Solving crossword puzzles requires diverse reasoning capabilities, acces...
research
04/08/2021

PQA: Perceptual Question Answering

Perceptual organization remains one of the very few established theories...

Please sign up or login with your details

Forgot password? Click here to reset