A Hybrid Framework for Topic Structure using Laughter Occurrences

TL;DR

This paper introduces a hybrid framework combining linguistic and paralinguistic cues, specifically laughter, to improve topic segmentation in multiparty meeting transcripts, enhancing discourse coherence analysis.

Contribution

It presents a novel hybrid, training-free approach that integrates laughter-based paralinguistic information with lexical cohesion for better topic structure detection.

Findings

Hybrid approach outperforms individual methods in topic segmentation.

Laughter occurrences provide valuable paralinguistic cues for discourse analysis.

Method applicable to online spoken dialog understanding.

Abstract

Conversational discourse coherence depends on both linguistic and paralinguistic phenomena. In this work we combine both paralinguistic and linguistic knowledge into a hybrid framework through a multi-level hierarchy. Thus it outputs the discourse-level topic structures. The laughter occurrences are used as paralinguistic information from the multiparty meeting transcripts of ICSI database. A clustering-based algorithm is proposed that chose the best topic-segment cluster from two independent, optimized clusters, namely, hierarchical agglomerative clustering and $K$-medoids. Then it is iteratively hybridized with an existing lexical cohesion based Bayesian topic segmentation framework. The hybrid approach improves the performance of both of the stand-alone approaches. This leads to the brief study of interactions between topic structures with discourse relational structure. This training-free topic structuring approach can be applicable to online understanding of spoken dialogs.