A Survey of Implicit Discourse Relation Recognition

TL;DR

This survey comprehensively reviews the task of implicit discourse relation recognition, covering its definitions, data sources, solution approaches, and future directions, highlighting its importance for NLP applications like summarization and translation.

Contribution

It provides an up-to-date, detailed categorization and analysis of methods for implicit discourse relation recognition, including performance comparisons and future research insights.

Findings

Performance benchmarks on a public corpus

Analysis of strengths and weaknesses of methods

Identification of promising future research directions

Abstract

A discourse containing one or more sentences describes daily issues and events for people to communicate their thoughts and opinions. As sentences are normally consist of multiple text segments, correct understanding of the theme of a discourse should take into consideration of the relations in between text segments. Although sometimes a connective exists in raw texts for conveying relations, it is more often the cases that no connective exists in between two text segments but some implicit relation does exist in between them. The task of implicit discourse relation recognition (IDRR) is to detect implicit relation and classify its sense between two text segments without a connective. Indeed, the IDRR task is important to diverse downstream natural language processing tasks, such as text summarization, machine translation and so on. This article provides a comprehensive and up-to-date survey for the IDRR task. We first summarize the task definition and data sources widely used in the field. We categorize the main solution approaches for the IDRR task from the viewpoint of its development history. In each solution category, we present and analyze the most representative methods, including their origins, ideas, strengths and weaknesses. We also present performance comparisons for those solutions experimented on a public corpus with standard data processing procedures. Finally, we discuss future research directions for discourse relation analysis.