Comparing Methods for Extractive Summarization of Call Centre Dialogue

TL;DR

This study evaluates extractive summarisation techniques for call centre dialogues, finding that simple heuristics like Lead-N and TopicSum outperform more complex models in producing meaningful call summaries.

Contribution

It provides a comparative analysis of extractive summarisation methods specifically for call centre dialogue summarization, highlighting effective simple heuristics.

Findings

TopicSum and Lead-N outperform other methods in evaluations.

BERTSum receives lower scores in both subjective and objective assessments.

Simple heuristics can produce meaningful call summaries.

Abstract

This paper provides results of evaluating some text summarisation techniques for the purpose of producing call summaries for contact centre solutions. We specifically focus on extractive summarisation methods, as they do not require any labelled data and are fairly quick and easy to implement for production use. We experimentally compare several such methods by using them to produce summaries of calls, and evaluating these summaries objectively (using ROUGE-L) and subjectively (by aggregating the judgements of several annotators). We found that TopicSum and Lead-N outperform the other summarisation methods, whilst BERTSum received comparatively lower scores in both subjective and objective evaluations. The results demonstrate that even such simple heuristics-based methods like Lead-N ca n produce meaningful and useful summaries of call centre dialogues.