Bansal’s research entails statistical natural language processing and machine learning, with a focus on multimodal, grounded, and embodied semantics (i.e., language with vision and speech, for robotics), human-like language generation and Q&A/dialogue, and interpretable and generalizable deep learning. One co-authored project entails efforts to build a generic framework for build text processing modules and linguistic resources which could be extended to all of the Indian languages.