Daniel Fried

I'm a final-year PhD student in the NLP Group and Berkeley AI Research Lab, advised by Dan Klein. Previously, I studied at the Cambridge Computer Laboratory and the University of Arizona, and interned with DeepMind, Microsoft Research, NAIST, and RWTH Aachen.

I'm grateful to be supported by a Google PhD Fellowship, and previously by Tencent AI Lab, Huawei/Berkeley AI, NDSEG and Churchill Foundation fellowships.

Email: dfried@berkeley.edu
Links: CV [pdf], [html]Google ScholarPapersTeachingResearch Statement [pdf], [html]
Daniel Fried

Research Summary

I work on natural language processing, specifically language grounding: interpreting and generating context-dependent language for real-world tasks like instruction following. When people communicate, they reason about the world and their conversational partners. Can natural language systems do the same? One effective approach to grounding is pragmatics: modeling people as cooperative agents who reason about each other. We've found that pragmatic reasoning improves NLP systems for interpreting (NeurIPS 2018) and generating (NAACL 2018, NAACL 2019) language. Another approach is modularity: building neural modules that decompose a complex task (ACL 2019, NAACL 2021). I'm also broadly interested in NLP, focusing recently on structured prediction (ACL 2020, TACL 2020) and syntactic parsing (ACL 2017, EMNLP 2017, ACL 2018, ACL 2019).