Search Results for author:
Found 3 papers, 2 papers with code
Data Augmentation for Low-Resource Dialogue Summarization
We present DADS, a novel Data Augmentation technique for low-resource Dialogue Summarization.
A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation
We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies.
Text Segmentation by Cross Segment Attention
Document and discourse segmentation are two fundamental NLP tasks pertaining to breaking up text into constituents, which are commonly used to help downstream tasks such as information retrieval or text summarization.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
