Automated Chess Commentator Powered by Neural Chess Engine

TL;DR

This paper presents a neural chess engine integrated with text generation models to produce automated chess commentary across various categories, demonstrating improved performance through joint training and evaluation on a benchmark dataset.

Contribution

It introduces a novel approach combining neural chess engines with commentary generation models, enhancing the quality and effectiveness of automated chess commentary.

Findings

Achieved high scores in automatic evaluations

Received positive feedback in human assessments

Demonstrated effectiveness across five commentary categories

Abstract

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.