Taxonomy of Abstractive Dialogue Summarization: Scenarios, Approaches and Future Directions

TL;DR

This survey comprehensively reviews abstractive dialogue summarization, categorizing approaches, datasets, and evaluation metrics, and discusses future research directions considering scenario-specific challenges and technical innovations.

Contribution

It provides a detailed taxonomy of existing techniques, datasets, and evaluation methods, and offers insights and future directions for abstractive dialogue summarization research.

Findings

Dialogue characteristics pose unique challenges for summarization.

Existing techniques are categorized into three main directions.

Future research should focus on complex scenarios and dataset availability.

Abstract

Abstractive dialogue summarization is to generate a concise and fluent summary covering the salient information in a dialogue among two or more interlocutors. It has attracted great attention in recent years based on the massive emergence of social communication platforms and an urgent requirement for efficient dialogue information understanding and digestion. Different from news or articles in traditional document summarization, dialogues bring unique characteristics and additional challenges, including different language styles and formats, scattered information, flexible discourse structures and unclear topic boundaries. This survey provides a comprehensive investigation on existing work for abstractive dialogue summarization from scenarios, approaches to evaluations. It categorizes the task into two broad categories according to the type of input dialogues, i.e., open-domain and task-oriented, and presents a taxonomy of existing techniques in three directions, namely, injecting dialogue features, designing auxiliary training tasks and using additional data.A list of datasets under different scenarios and widely-accepted evaluation metrics are summarized for completeness. After that, the trends of scenarios and techniques are summarized, together with deep insights on correlations between extensively exploited features and different scenarios. Based on these analyses, we recommend future directions including more controlled and complicated scenarios, technical innovations and comparisons, publicly available datasets in special domains, etc.