Leveraging summarization for unsupervised topic segmentation of long dialogues

Anonymous

Abstract: Traditional approaches to dialogue segmentation perform quite well on synthetic or short dialogues but suffer when dealing with long, noisy dialogs. In addition, such methods require careful tuning of hyperparameters. We propose to leverage a novel approach that is based on dialogue summaries. Experiments on different datasets showed that the new approach outperforms popular SotA algorithms in unsupervised topic segmentation and requires less setup.

Paper Type: short

Research Area: Dialogue and Interactive Systems

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Approaches to low-resource settings, Data analysis

Languages Studied: english

Consent To Share Submission Details: On behalf of all authors, we agree to the terms above to share our submission details.