Decrypting Cryptic Crosswords: Semantically Complex Wordplay Puzzles as a Target for NLP

TL;DR

This paper introduces a new cryptic crossword dataset as a challenging benchmark for NLP, evaluates existing models, and proposes a curriculum fine-tuning approach to improve their understanding of complex, creative language puzzles.

Contribution

It provides a novel dataset and benchmark for cryptic crossword clues, and develops a curriculum-based fine-tuning method to enhance NLP models' ability to solve complex, compositional language puzzles.

Findings

Neural models underperform on cryptic clues

Curriculum fine-tuning improves model performance

Models show partial human-like solving strategies

Abstract

Cryptic crosswords, the dominant crossword variety in the UK, are a promising target for advancing NLP systems that seek to process semantically complex, highly compositional language. Cryptic clues read like fluent natural language but are adversarially composed of two parts: a definition and a wordplay cipher requiring character-level manipulations. Expert humans use creative intelligence to solve cryptics, flexibly combining linguistic, world, and domain knowledge. In this paper, we make two main contributions. First, we present a dataset of cryptic clues as a challenging new benchmark for NLP systems that seek to process compositional language in more creative, human-like ways. After showing that three non-neural approaches and T5, a state-of-the-art neural language model, do not achieve good performance, we make our second main contribution: a novel curriculum approach, in which the model is first fine-tuned on related tasks such as unscrambling words.We also introduce a challenging data split, examine the meta-linguistic capabilities of subword-tokenized models, and investigate model systematicity by perturbing the wordplay part of clues, showing that T5 exhibits behavior partially consistent with human solving strategies. Although our curricular approach considerably improves on the T5 baseline, our best-performing model still fails to generalize to the extent that humans can. Thus, cryptic crosswords remain an unsolved challenge for NLP systems and a potential source of future innovation.