PhD Student, Department of Computer Science, University of California, Irvine
- Date & time
- Monday, March 1, 2021 · 1:00 PM
- Location
- Online (live stream)
Abstract
Recent progress in NLP has been driven by large neural language models (e.g., GPT-2 and BERT) that are pretrained using self-supervised learning before being finetuned to downstream tasks. In this talk, we describe the technique of prompting, which reformulates tasks as fill-in-the-blank questions. We show how prompts can measure the factual, linguistic, and task-specific knowledge contained in language models, introduce an approach for automatically constructing prompts via gradient-guided search, and cover ongoing work investigating whether prompting can replace finetuning — with early results showing prompting can be more effective in few-shot scenarios while being substantially more parameter efficient.
About the speaker
Robert L. Logan IV is a 4th-year PhD Candidate at UC Irvine, co-advised by Sameer Singh and Padhraic Smyth. His research focuses on leveraging external knowledge sources to measure and improve NLP models' ability to reason with factual and common-sense knowledge. He was selected as a Noyce Fellow and awarded the 2020 Rose Hills Foundation Scholarship.