TL;DR
This paper investigates how discourse structure and context influence the classification of discourse relations in scientific writing, highlighting the potential of PLMs and LLMs to improve understanding of scientific texts.
Contribution
It provides a preliminary analysis of the effectiveness of pretrained and large language models in classifying discourse relations within scientific publications, emphasizing the role of context.
Findings
Context generally improves discourse relation classification.
Certain scientific discourse relation types benefit more from context.
PLMs and LLMs show promise in understanding scientific discourse.
Abstract
With the increasing use of generative Artificial Intelligence (AI) methods to support science workflows, we are interested in the use of discourse-level information to find supporting evidence for AI generated scientific claims. A first step towards this objective is to examine the task of inferring discourse structure in scientific writing. In this work, we present a preliminary investigation of pretrained language model (PLM) and Large Language Model (LLM) approaches for Discourse Relation Classification (DRC), focusing on scientific publications, an under-studied genre for this task. We examine how context can help with the DRC task, with our experiments showing that context, as defined by discourse structure, is generally helpful. We also present an analysis of which scientific discourse relation types might benefit most from context.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
