Despite many recent advancements in language modeling, state-of-the-art language models lack grounding in the real world and struggle with tasks involving complex reasoning. Meanwhile, advances in the symbolic reasoning capabilities of AI have led to systems that outperform humans in games like chess and Go (Silver et al., 2018). Chess commentary provides an interesting domain for bridging these two fields of research, as it requires reasoning over a complex board state and providing analyses in natural language. In this work we demonstrate how to combine symbolic reasoning engines with controllable language models to generate chess commentaries. We conduct experiments to demonstrate that our approach generates commentaries that are preferred by human judges over previous baselines.
翻译:尽管最近在语言建模方面有许多进步,但最先进的语言模型缺乏在现实世界的基础,与涉及复杂推理的任务挣扎不休。与此同时,AI的象征性推理能力的进步导致象棋和戈等游戏中人类表现优于人类的系统(Silver等人,2018年)。象棋评注为连接这两个研究领域提供了一个有趣的领域,因为它要求对复杂的董事会状态进行推理,并以自然语言进行分析。在这项工作中,我们展示了如何将象征性推理引擎与可控制的语言模型相结合,以生成象棋评论。我们进行了实验,以证明我们的方法所产生的评论是人类法官比先前的基线更喜欢的。