A Cross-Genre Analysis of Discourse Relation Signaling in the GUM Corpus

2026-01-13 · Source: Paper Index on ACL Anthology · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics · Depth: Expert, quick

Summary

Lauren Levine's 2025 paper, "A Cross-Genre Analysis of Discourse Relation Signaling in the GUM Corpus," investigates how discourse relations are signaled across various text genres within the GUM Corpus. Published in the Proceedings of the Society for Computation in Linguistics 2025, this work contributes to the understanding of linguistic mechanisms that convey relationships between clauses and sentences. The analysis spans pages 300-308 and was presented in Eugene, Oregon, under the editorship of Carolyn Jane Anderson, Frédéric Mailhot, and Grusha Prasad. This research is part of the broader efforts by the Association for Computational Linguistics to advance the field of computational linguistics, specifically focusing on discourse analysis and corpus linguistics.

Key takeaway

For AI scientists developing natural language understanding models, understanding genre-specific discourse relation signaling is crucial. Your models will achieve higher accuracy and contextual relevance by incorporating these genre-dependent patterns, especially when processing diverse text types. Consider fine-tuning your NLU systems on genre-specific discourse markers identified through corpus analysis to improve coherence and relational understanding.

Key insights

The paper analyzes discourse relation signaling across diverse genres in the GUM Corpus.

Principles

• Discourse signaling varies by genre.
• Corpus analysis reveals linguistic patterns.

Method

The method involves a cross-genre analysis of discourse relation signaling within the GUM Corpus, examining linguistic features that indicate relationships between textual units.

In practice

• Apply genre-specific discourse models.
• Utilize GUM Corpus for linguistic studies.

Topics

• Discourse Relations
• GUM Corpus
• Cross-Genre Analysis
• Computational Linguistics
• Natural Language Processing

Best for: AI Scientist, AI Researcher, Research Scientist, AI Student

Related on AIssential

• Discourse Relations and Connectives in Higher Text Structure — Local discourse analysis can reveal clues about higher text structure and global coherence.
• On GATE, Text and Social Media Analysis, and Detecting Misinformation Online — A multi-layer analytical pipeline effectively extracts and categorizes digital identity aspects of agrifood products from online discourse.
• Mapping the Political Discourse in the Brazilian Chamber of Deputies: A Multi-Faceted Computational Approach — Computational methods can reveal hidden patterns in parliamentary discourse beyond voting records.
• How Mathematics Won AI — A Story in Three Acts — AI, especially NLP, shifted from linguistic theory to mathematical models, prioritizing performance over explicit language understanding.
• Rhetorical Questions in LLM Representations: A Linear Probing Study — LLMs encode rhetorical questions via multiple linear directions, emphasizing distinct cues rather than a single shared representation.
• Which sentence is doing the most work in your favourite novel ? I tried to find out. — Machine learning can identify semantically distinctive sentences in texts, revealing structural or narrative pivots.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Paper Index on ACL Anthology.