Automated Chess Commentator Powered by Neural Chess Engine
This work addresses the problem of generating diverse chess commentary for players and enthusiasts, representing an incremental improvement in AI-driven game analysis.
The paper tackled automated chess commentary generation by integrating a neural chess engine with text generation models, achieving inspiring results in both automatic and human evaluations across five categories.
In this paper, we explore a new approach for automated chess commentary generation, which aims to generate chess commentary texts in different categories (e.g., description, comparison, planning, etc.). We introduce a neural chess engine into text generation models to help with encoding boards, predicting moves, and analyzing situations. By jointly training the neural chess engine and the generation models for different categories, the models become more effective. We conduct experiments on 5 categories in a benchmark Chess Commentary dataset and achieve inspiring results in both automatic and human evaluations.