2021/04/12 by Roshanak Mirzaee, Hossein Rajaby Faghihi, Mirzaee, Roshanak +5 · 10 citations
Computer Science · #Multimodal Machine Learning Applications #Speech and dialogue systems #Natural Language Processing Techniques
paper · pdf · doi:10.48550/arxiv.2104.05832
This paper proposes a question-answering (QA) benchmark for spatial reasoning on natural language text which contains more realistic spatial phenomena not covered by prior work and is challenging for state-of-the-art language models (LM). We propose a distant supervision method to improve on this task. Specifically, we design grammar and reasoning rules to automatically generate a spatial description of visual scenes and corresponding QA pairs. Experiments show that further pretraining LMs on these automatically generated data significantly improves LMs' capability on spatial understanding, which in turn helps to better solve two external datasets, bAbI, and boolQ. We hope that this work can foster investigations into more sophisticated models for spatial reasoning over text.