Neuro-symbolic Training for Reasoning over Spatial Language
This addresses a crucial problem for machines needing human-like spatial reasoning abilities, but it appears incremental as it builds on existing neuro-symbolic techniques for a specific bottleneck.
The paper tackled the problem of spatial reasoning over natural language, where state-of-the-art language models struggle with nesting expressions, by proposing neuro-symbolic training that uses spatial logical rules as constraints to improve reasoning and question answering. The results show effectiveness in improving language models for complex multi-hop spatial reasoning over text on existing benchmarks.
Spatial reasoning based on natural language expressions is essential for everyday human tasks. This reasoning ability is also crucial for machines to interact with their environment in a human-like manner. However, recent research shows that even state-of-the-art language models struggle with spatial reasoning over text, especially when facing nesting spatial expressions. This is attributed to not achieving the right level of abstraction required for generalizability. To alleviate this issue, we propose training language models with neuro-symbolic techniques that exploit the spatial logical rules as constraints, providing additional supervision to improve spatial reasoning and question answering. Training language models to adhere to spatial reasoning rules guides them in making more effective and general abstractions for transferring spatial knowledge to various domains. We evaluate our approach on existing spatial question-answering benchmarks. Our results indicate the effectiveness of our proposed technique in improving language models in complex multi-hop spatial reasoning over text.