# Dissecting Content and Context in Argumentative Relation Analysis

arXiv: https://arxiv.org/abs/1906.03338 · HTML: https://mlsanity.com/paper/1906.03338/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2019.

## Built on by (most cited first, 10 of 10)

- [Classifying Argumentative Relations Using Logical Mechanisms and Argumentation Schemes](https://mlsanity.com/paper/2105.07571/) (2021)
- [Scientia Potentia Est -- On the Role of Knowledge in Computational Argumentation](https://mlsanity.com/paper/2107.00281/) (2021)
- [Contextual information integration for stance detection via cross-attention](https://mlsanity.com/paper/2211.01874/) (2022)
- [Can Unsupervised Knowledge Transfer from Social Discussions Help Argument Mining?](https://mlsanity.com/paper/2203.12881/) (2022)
- [Efficient Argument Structure Extraction with Transfer Learning and Active Learning](https://mlsanity.com/paper/2204.00707/) (2022)
- [Limited Generalizability in Argument Mining: State-Of-The-Art Models Learn Datasets, Not Arguments](https://mlsanity.com/paper/2505.22137/) (2025)
- [Contextual Argument Component Classification for Class Discussions](https://mlsanity.com/paper/2102.10290/) (2021)
- [Cross-Genre Argument Mining: Can Language Models Automatically Fill in Missing Discourse Markers?](https://mlsanity.com/paper/2306.04314/) (2023)
- [Enhancing Argument Structure Extraction with Efficient Leverage of Contextual Information](https://mlsanity.com/paper/2310.05073/) (2023)
- [An LLM-Based System for Argument Mining](https://mlsanity.com/paper/2605.13793/) (2026)

## Abstract (arXiv)

When assessing relations between argumentative units (e.g., support or attack), computational systems often exploit disclosing indicators or markers that are not part of elementary argumentative units (EAUs) themselves, but are gained from their context (position in paragraph, preceding tokens, etc.). We show that this dependency is much stronger than previously assumed. In fact, we show that by completely masking the EAU text spans and only feeding information from their context, a competitive system may function even better. We argue that an argument analysis system that relies more on discourse context than the argument's content is unsafe, since it can easily be tricked. To alleviate this issue, we separate argumentative units from their context such that the system is forced to model and rely on an EAU's content. We show that the resulting classification system is more robust, and argue that such models are better suited for predicting argumentative relations across documents.