ServiceNow Research

S-LLM: Semi-Supervised Large Language Model for Chat Summarization

Abstract

As producing high-quality summaries of chat dialogues currently requires large labeled datasets, we propose a method to efficiently leverage unlabeled data. Using a pseudo-labeling approach and post-processing to improve the quality of the pseudo-summaries, we are able to improve the Rouge-2 score of DistilBART by more than 6 points when using only 1% of labeled data on the TWEETSUMM dataset.

Publication
Montreal AI Symposium (MAIS)
Issam H. Laradji
Issam H. Laradji
Research Scientist

Research Scientist at Low Data Learning located at Vancouver, BC, Canada.

Orlando Marquez
Orlando Marquez
Applied Research Scientist

Applied Research Scientist at Azimuth located at Montreal, QC, Canada.

David Vazquez
David Vazquez
Manager of Research Programs

Manager of Research Programs at Research Management located at Montreal, QC, Canada.