2022/12/15 by Andrew Lee, Lee, Andrew, David Wu +5 · 1 voice · 2 citations
Computer Science · Economics, Econometrics and Finance · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Sports Analytics and Performance #Topic Modeling #cs.CL
paper · pdf · doi:10.48550/arxiv.2212.08195
openalex publication_date 2022/12/15 · arxiv published 2022/12/15 · arxiv updated 2022/12/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.