Full-Text Argumentation Mining on Scientific Publications

TL;DR

This paper introduces a sequential pipeline model for full-text scholarly argumentation mining, achieving state-of-the-art results in argument discourse unit recognition and pioneering results in argument relation extraction, highlighting key challenges and future directions.

Contribution

It presents the first full-text argumentation mining pipeline combining ADUR and ARE, with improved performance and comprehensive analysis on scientific publications.

Findings

State-of-the-art ADUR performance (+7% F1) on Sci-Arg corpus

First results for argument relation extraction in scholarly texts

Identifies major challenges like non-contiguous ADUs and discourse connector interpretation

Abstract

Scholarly Argumentation Mining (SAM) has recently gained attention due to its potential to help scholars with the rapid growth of published scientific literature. It comprises two subtasks: argumentative discourse unit recognition (ADUR) and argumentative relation extraction (ARE), both of which are challenging since they require e.g. the integration of domain knowledge, the detection of implicit statements, and the disambiguation of argument structure. While previous work focused on dataset construction and baseline methods for specific document sections, such as abstract or results, full-text scholarly argumentation mining has seen little progress. In this work, we introduce a sequential pipeline model combining ADUR and ARE for full-text SAM, and provide a first analysis of the performance of pretrained language models (PLMs) on both subtasks. We establish a new SotA for ADUR on the Sci-Arg corpus, outperforming the previous best reported result by a large margin (+7% F1). We also present the first results for ARE, and thus for the full AM pipeline, on this benchmark dataset. Our detailed error analysis reveals that non-contiguous ADUs as well as the interpretation of discourse connectors pose major challenges and that data annotation needs to be more consistent.