Daniel Fried

I will be starting as an assistant professor at the Language Technologies Institute in the School of Computer Science at Carnegie Mellon in Fall 2022.

I'm currently (until July 2022) a visiting researcher / postdoc at FAIR Seattle and the University of Washington, working with Mike Lewis and Luke Zettlemoyer.

Previously, I completed a PhD at UC Berkeley in the NLP Group and the Berkeley AI Research Lab, an M.Phil. at the Cambridge Computer Laboratory and a B.S. at the University of Arizona.

Links: Google ScholarCV [pdf], [html] Research Statement [pdf], [html]Teaching
Email: dfried@cs.cmu.edu • (note for prospective students) • Twitter: @dan_fried
Daniel Fried


Research Summary

I work on grounding and interaction in natural language processing (NLP). Language is a multi-agent system, and when people communicate with each other, they reason about the world and their conversational partners. Can our NLP agents do the same?

One recurring theme in my work is pragmatics: viewing language as an action that people take in context to affect other agents and the world. This has helped us build NLP systems that more successfully interact with people when generating (EMNLP 2021, NAACL 2018, NAACL 2019) and interpreting (ACL 2022, NeurIPS 2018) language. My work often also ends up using modularity: neural modules that decompose a complex task (EMNLP 2021, NAACL 2021, ACL 2019). Here is my job talk with an overview of our work.

I'm also interested in language-to-code (InCoder, MBR-Exec) and structured prediction generally (ACL 2020, TACL 2020, ACL 2018).



Preprints

Publications

Teaching

Course Materials

Teaching Experience