PDF] Automated Chess Commentator Powered by Neural Chess Engine

A neural chess engine is introduced 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, which become more effective. 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.

PDF] Automated Chess Commentator Powered by Neural Chess Engine

PDF] Improving Chess Commentaries by Combining Language Models

PDF] Learning to Generate Move-by-Move Commentary for Chess Games

Acquisition of chess knowledge in AlphaZero

Automated Chess Commentator Powered by Neural Chess Engine - ACL

Sensors, Free Full-Text

The human side of AI for chess - Microsoft Research

Acquisition of chess knowledge in AlphaZero

Entropy, Free Full-Text

Overview ChessCoach

Recent advances and applications of deep learning methods in

PDF] Learning a game commentary generator with grounded move

Mastering the game of Go with deep neural networks and tree search