Automated Chess Commentator Powered by Neural Chess Engine

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5952–5961 Florence, Italy, July 28 - August 2, 2019. c⃝2019 Association for Computational Linguistics 5952 Automated Chess Commentator Powered by Neural Chess Engine Hongyu Zang∗and Zhiwei Yu∗and Xiaojun Wan Institute of Computer Science and Technology, Peking University The MOE Key Laboratory of Computational Linguistics, Peking University {zanghy, yuzw, wanxiaojun}@pku.edu.cn 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 mod- els to help with encoding boards, predicting moves, and analyzing situations. By jointly training the neural chess engine and the gener- ation models for different categories, the mod- els become more effective. We conduct exper- iments on 5 categories in a benchmark Chess Commentary dataset and achieve inspiring re- sults in both automatic and human evaluations. 1 Introduction With games exploding in popularity, the demand for Natural Language Generation (NLG) applica- tions for games is growing rapidly. Related re- searches about generating real-time game reports (Yao et al., 2017), comments (Jhamtani et al., 2018; Kameko et al., 2015), and tutorials (Green et al., 2018a,b) benefit people with entertainments and learning materials. Among these, chess com- mentary is a typical task. As illustrated in Fig- ure 1, the commentators need to understand the current board and move. And then they comment about the current move (Description), their judg- ment about the move (Quality), the game situation for both sides (Contexts), their analysis (Compar- ison) and guesses about player’s strategy (Plan- ning). The comments provide valuable informa- tion about what is going on and what will happen. Such information not only make the game more enjoyable for the viewers, but also help them learn to think and play. Our task is to design automated generation model to address all the 5 sub-tasks (Description, Quality, Comparison, Planning, and Contexts) of single-move chess commentary. ∗The two authors contributed equally to this paper. Figure 1: Chess Commentary Examples. Automatically generating chess comments draws attention from researchers for a long time. Traditional template-based methods (Sadikov et al., 2007) are precise but limited in template variety. With the development of deep learning, data-driven methods using neural networks are proposed to produce comments with high quality and flexibility. However, generating insightful comments (e.g., to explain why a move is better than the others) is still very challenging. Current neural approaches (Kameko et al., 2015; Jhamtani et al., 2018) get semantic representations from raw boards, moves, and evaluation information (threats and scores) from external chess engines. Such methods can easily ground comments to cur- rent boards and moves. But they cannot provide sufficient analysis on what will happen next in the game. Although external features are provided by powerful chess engines, the features are not in a continuous space, which may be not very suitable for context modeling and commentary generation. It is common knowledge that professional game …

Content truncated to 500 words