Unsupervised Summarization for Chat Logs with Topic-Oriented Ranking and Context-Aware Auto-Encoders

TL;DR

This paper introduces RankAE, an unsupervised framework for chat log summarization that uses topic-oriented ranking and context-aware auto-encoders to generate relevant summaries without labeled data.

Contribution

The work presents a novel unsupervised approach combining topic ranking and denoising auto-encoders specifically designed for chat log summarization.

Findings

RankAE outperforms other unsupervised methods in relevance and topic coverage.

The method effectively handles fragmented and evolving chat topics.

Experimental results demonstrate high-quality, context-aware summaries.

Abstract

Automatic chat summarization can help people quickly grasp important information from numerous chat messages. Unlike conventional documents, chat logs usually have fragmented and evolving topics. In addition, these logs contain a quantity of elliptical and interrogative sentences, which make the chat summarization highly context dependent. In this work, we propose a novel unsupervised framework called RankAE to perform chat summarization without employing manually labeled data. RankAE consists of a topic-oriented ranking strategy that selects topic utterances according to centrality and diversity simultaneously, as well as a denoising auto-encoder that is carefully designed to generate succinct but context-informative summaries based on the selected utterances. To evaluate the proposed method, we collect a large-scale dataset of chat logs from a customer service environment and build an annotated set only for model evaluation. Experimental results show that RankAE significantly outperforms other unsupervised methods and is able to generate high-quality summaries in terms of relevance and topic coverage.