Unpacking Ambiguity: The Interaction of Polysemous Discourse Markers and Non-DM Signals

2025-07-22

AI Summary

This study investigates the interaction between discourse marker (DM) polysemy and co-occurring non-DM signals (e.g., syntactic structures, punctuation), and their joint impact on textual coherence and ambiguity resolution—particularly examining genre as a moderating factor. Methodologically, it proposes a gradient definition of DM polysemy grounded in enhanced Rhetorical Structure Theory (eRST), and employs relevance analysis and regression modeling to quantify co-occurrence patterns between DMs and non-DM signals. Results show that polysemous DMs tend to co-occur with a *greater diversity*—rather than higher frequency—of non-DM signals; that non-DM signal combinations are genre-specific and significantly modulate DM sense disambiguation; and that a systematic triadic relationship exists among DM polysemy, signal diversity, and genre constraints. The study contributes a computationally tractable, cross-signal collaborative model for DM ambiguity resolution, advancing discourse analysis from single-marker-centric approaches toward a multimodal, signal-interaction paradigm.

Technology Category

• Natural Language Processing: Discourse, Pragmatics & Argument Mining
• Knowledge Representation and Reasoning: Argumentation
• Data Mining & Knowledge Management: Semantic Web

Application Category

• Semantics and Knowledge: Provenance, trust, security and privacy, and ethical issues in managing semantic data
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Discourse markers (DMs) like 'but' or 'then' are crucial for creating coherence in discourse, yet they are often replaced by or co-occur with non-DMs ('in the morning' can mean the same as 'then'), and both can be ambiguous ('since' can refer to time or cause). The interaction mechanism between such signals remains unclear but pivotal for their disambiguation. In this paper we investigate the relationship between DM polysemy and co-occurrence of non-DM signals in English, as well as the influence of genre on these patterns. Using the framework of eRST, we propose a graded definition of DM polysemy, and conduct correlation and regression analyses to examine whether polysemous DMs are accompanied by more numerous and diverse non-DM signals. Our findings reveal that while polysemous DMs do co-occur with more diverse non-DMs, the total number of co-occurring signals does not necessarily increase. Moreover, genre plays a significant role in shaping DM-signal interactions.

Problem

• Investigates interaction between polysemous discourse markers and non-DM signals
• Explores ambiguity resolution of DMs like 'but' and 'then' in English
• Examines genre influence on DM and non-DM signal co-occurrence patterns

Innovation

• Proposed graded DM polysemy definition
• Used correlation and regression analyses
• Examined genre influence on signals