Search Results for author:
Found 3 papers, 3 papers with code
Revisiting Topic-Guided Language Models
A recent line of work in natural language processing has aimed to combine language models and topic models.
An Invariant Learning Characterization of Controlled Text Generation
In this paper, we show that the performance of controlled generation may be poor if the distributions of text in response to user prompts differ from the distribution the predictor was trained on.
Complexity-Weighted Loss and Diverse Reranking for Sentence Simplification
Sentence simplification is the task of rewriting texts so they are easier to understand.
Ranked #4 on
Text Simplification
on Newsela
Cannot find the paper you are looking for? You can
Submit a new open access paper.
