Down and Across: Introducing Crossword-Solving as a New NLP Benchmark
This work addresses the need for a diverse reasoning and knowledge-based benchmark in NLP, though it is incremental as it primarily introduces a new dataset and baseline methods.
The authors introduced solving crossword puzzles as a new NLP benchmark, releasing a dataset of around 9,000 puzzles from the New York Times with over half a million clue-answer pairs, and proposed baselines and evaluation metrics for this task.
Solving crossword puzzles requires diverse reasoning capabilities, access to a vast amount of knowledge about language and the world, and the ability to satisfy the constraints imposed by the structure of the puzzle. In this work, we introduce solving crossword puzzles as a new natural language understanding task. We release the specification of a corpus of crossword puzzles collected from the New York Times daily crossword spanning 25 years and comprised of a total of around nine thousand puzzles. These puzzles include a diverse set of clues: historic, factual, word meaning, synonyms/antonyms, fill-in-the-blank, abbreviations, prefixes/suffixes, wordplay, and cross-lingual, as well as clues that depend on the answers to other clues. We separately release the clue-answer pairs from these puzzles as an open-domain question answering dataset containing over half a million unique clue-answer pairs. For the question answering task, our baselines include several sequence-to-sequence and retrieval-based generative models. We also introduce a non-parametric constraint satisfaction baseline for solving the entire crossword puzzle. Finally, we propose an evaluation framework which consists of several complementary performance metrics.