Learning a game commentary generator with grounded move expressions
Learning a game commentary generator with grounded move expressions
复制标题
DOI：
10.1109/cig.2015.7317930
复制
发表时间：
2015-11
期刊：
影响因子：
--
通讯作者：
Hirotaka Kameko;Shinsuke Mori;Yoshimasa Tsuruoka
中科院分区：
文献类型：
--
作者：
Hirotaka Kameko;Shinsuke Mori;Yoshimasa Tsuruoka
本文描述了一种基于机器学习的方法，用于生成Shogi游戏的自然语言评论。我们通过使用一个判别语言模型来生成评论，该模型由大量的Shogi游戏记录和人类专家的评论训练而成。我们方法的核心是将专家评论中的移动表达式精确映射到棋棋的游戏状态（即棋棋的位置），因为判别语言模型是用与相应的棋棋位置配对的文本表达式来训练的。我们描述了如何通过使用从Shogi程序中获得的评估信息来执行这种映射。实验结果表明，我们确实可以为某些职位生成有用的评论。
This paper describes a machine learning-based approach for generating natural language comments on Shogi games. We generate comments by using a discriminative language model trained with a large amount of Shogi game records and comments made by human experts. Central to our method is accurate mapping of move expressions appearing in experts' comments to game states (i.e. positions) of Shogi, because the discriminative language model is trained with textual expressions paired with corresponding Shogi positions. We describe how such mapping can be performed by using evaluation information obtained from a Shogi program. Experimental results show that we can actually generate helpful comments for some positions.