DiscoExplorer: An Open Interface for the Study of Multilingual Discourse Relations

2026-05-14

AI Summary

This work addresses the longstanding challenge in cross-linguistic discourse relation research—namely, the absence of standardized resources and efficient analytical tools. The authors propose DiscoExplorer, an open-source, locally deployable interactive web platform that integrates, for the first time, standardized discourse relation annotations across 16 languages from the DISRPT shared task. The system enables flexible querying, retrieval, and visualization of discourse relations such as causality and concession, along with their associated signals (e.g., connectives). Built upon a dedicated query language and a structured data model, DiscoExplorer substantially lowers the barrier to entry for cross-linguistic discourse analysis. Empirical evaluation demonstrates its effectiveness in supporting the exploration and comparison of complex multilingual discourse phenomena, offering a practical infrastructure for future research in this domain.

Abstract

The relations connecting propositions in discourse such as cause (A because B) or concession (A although B) are a subject of intense interest in Computational Linguistics and Pragmatics, but challenging to study and compare across languages. Recent progress in standardizing discourse relation inventories across datasets offers the potential to facilitate such studies, but is hindered by the complexity of relevant data and the lack of easily accessible interfaces to analyze it. In this paper we present DiscoExplorer, a new open source web interface, capable of running on local computers, which we use to make datasets from the DISRPT Shared Task on discourse relation classification publicly available, covering 16 different languages. We present the query language, search and visualization facilities for relations and signaling devices such as connectives, as well as some example studies.

Problem

• discourse relations
• multilingual
• computational linguistics
• pragmatics
• cross-lingual comparison

Innovation

• DiscoExplorer
• discourse relations
• multilingual
• open-source interface
• DISRPT