My goal is to develop general-purpose AI algorithms that represent, comprehend, and reason about diverse forms of data at large scale. I mainly publish at NLP conferences (ACL, NAACL, EMNLP), AI and ML conferences (AAAI, ICLR). Toward this end, my lab (H2lab) focuses on research efforts to address foundational problems in NLP, AI and Machine Learning:

Representation learning for multimodal data: (a) Integrating neural and structured representations to encode diverse forms of data into knowledge-aware dense vectors, (b) learning efficient neural network architectures for representing textual and visual data.
Question Answering and Reasoning: Developing interpretable and efficient reasoning algorithms for (a) general-purpose multi-hop, multi-modal, and knowledge-aware question answering, (b) addressing questions about textbooks and math word problems.
Knowledge Graphs: Extracting information about entities, relations, and events from text including web data, news articles, and scientific articles.
NLP Applications: Establishing scalable, real-world applications such as open-domain question answering, information extraction, and conversational dialogs.