7 citations · 31 across the 11 of their papers we have counts for
3 papers · 1 filter
Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference
Eric Mitchell, Joseph J. Noh, Siyan Li +5
While large pre-trained language models are powerful, their predictions often lack logical consistency across test inputs. For example, a state-of-the-art Macaw question-answering…
Systematicity in GPT-3's Interpretation of Novel English Noun Compounds
Siyan Li, Riley Carlson, Christopher Potts
Levin et al. (2019) show experimentally that the interpretations of novel English noun compounds (e.g., stew skillet), while not fully compositional, are highly predictable based o…
When can I Speak? Predicting initiation points for spoken dialogue agents
Siyan Li, Ashwin Paranjape, Christopher D. Manning
Current spoken dialogue systems initiate their turns after a long period of silence (700-1000ms), which leads to little real-time feedback, sluggish responses, and an overall stilt…