M$^3$Seg: A Maximum-Minimum Mutual Information Paradigm for Unsupervised Topic Segmentation in ASR Transcripts
Submission Type: Regular Short Paper
Submission Track: Semantics: Lexical, Sentence level, Document Level, Textual Inference, etc.
Submission Track 2: NLP Applications
Keywords: Unsupervised topic segmentation, mutual information maximization/minimization, automatic-speech-recognition (ASR) transcripts structuring
Abstract: Topic segmentation aims to detect topic boundaries and split automatic speech recognition transcriptions (e.g., meeting transcripts) into segments that are bounded by thematic meanings.
In this work, we propose M$^3$Seg, a novel Maximum-Minimum Mutual information paradigm for linear topic segmentation without using any parallel data.
Specifically, by employing sentence representations provided by pre-trained language models, M$^3$Seg first learns a region-based segment encoder based on the maximization of mutual information between the global segment representation and the local contextual sentence representation.
Secondly, an edge-based boundary detection module aims to segment the whole by topics based on minimizing the mutual information between different segments.
Experiment results on two public datasets demonstrate the effectiveness of M$^3$Seg, which outperform the state-of-the-art methods by a significant (18\%–37\% improvement) margin.
Submission Number: 2768
Loading