Dr. Dipanjan Das
Director of Research
Google Deepmind
USA
Dipanjan Das is a Director of Research at Google Deepmind, based in New York City. He leads teams of researchers distributed between New York, London, Berlin, Seattle and Amsterdam focusing on language technologies. His research focus is on detecting and modeling factuality and groundedness in language models. Prior to joining Google, he completed a Ph.D. from the Language Technologies Institute, School of Computer Science at Carnegie Mellon University in 2012. In 2005, he completed a B.Tech. in Computer Science and Engineering from IIT Kharagpur. His work has received paper awards at the ACL and EMNLP conferences; he has served as action editor for the Transactions of the Association for Computational Linguistics and the ACL Rolling Review and as senior committee member at various *ACL and machine learning venues.
Lecture abstract: Trustworthy Natural Language Generation with Communicative Goals While language generation via learned models is commonplace in practical scenarios today, such models still suffer from content "hallucination", where model-generated statements are not attributable to sources in communicative scenarios (e.g. summarization, question answering and responses in dialogue systems). Furthermore, evaluation of generation systems remains challenging: (1) human evaluation studies are not reproducible and there is a lack of common benchmarking for diverse tasks, and (2) popular automatic evaluation methods correlate poorly with human judgments. In this talk, I will present a body of work that attempts to solve the above problems for a variety of natural language generation problems, presents a few "controllable" modeling recipes, and showcases a vision towards future work in this area.