activity
20192022
most citedGenerating Sequences by Learning to Self-Correct

30 citations · 31 across the 3 of their papers we have counts for

collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL202230 cited

Generating Sequences by Learning to Self-Correct

Sean Welleck, Ximing Lu, Peter West +4

Sequence generation applications require satisfying semantic constraints, such as ensuring that programs are correct, using certain keywords, or avoiding undesirable content. Langu…

cs.CL20221 cited

Referee: Reference-Free Sentence Summarization with Sharper Controllability through Symbolic Knowledge Distillation

Melanie Sclar, Peter West, Sachin Kumar +2

We present Referee, a novel framework for sentence summarization that can be trained reference-free (i.e., requiring no gold summaries for supervision), while allowing direct contr…

cs.CL2022

Probing Factually Grounded Content Transfer with Factual Ablation

Peter West, Chris Quirk, Michel Galley +1

Despite recent success, large neural models often generate factually incorrect text. Compounding this is the lack of a standard automatic evaluation for factuality--it cannot be me…

cs.CL2020

NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints

Ximing Lu, Peter West, Rowan Zellers +3

Conditional text generation often requires lexical constraints, i.e., which words should or shouldn't be included in the output text. While the dominant recipe for conditional text…

cs.CL2020

Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning

Lianhui Qin, Vered Shwartz, Peter West +5

Abductive and counterfactual reasoning, core abilities of everyday human cognition, require reasoning about what might have happened at time t, while conditioning on multiple conte…

cs.CL2020

Unsupervised Commonsense Question Answering with Self-Talk

Vered Shwartz, Peter West, Ronan Le Bras +2

Natural language understanding involves reading between the lines with implicit background knowledge. Current systems either rely on pre-trained language models as the sole implici…