# Fine-Grained Argument Unit Recognition and Classification

arXiv: https://arxiv.org/abs/1904.09688 · HTML: https://mlsanity.com/paper/1904.09688/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2019.

## Built on by (most cited first, 26 of 26)

- [DISAPERE: A Dataset for Discourse Structure in Peer Review Discussions](https://mlsanity.com/paper/2110.08520/) (2021)
- [Empowering the Fact-checkers! Automatic Identification of Claim Spans on Twitter](https://mlsanity.com/paper/2210.04710/) (2022)
- [Scientia Potentia Est -- On the Role of Knowledge in Computational Argumentation](https://mlsanity.com/paper/2107.00281/) (2021)
- [Crowdsourcing Learning as Domain Adaptation: A Case Study on Named Entity Recognition](https://mlsanity.com/paper/2105.14980/) (2021)
- [Which Side Are You On? A Multi-task Dataset for End-to-End Argument Summarisation and Evaluation](https://mlsanity.com/paper/2406.03151/) (2024)
- [LMTurk: Few-Shot Learners as Crowdsourcing Workers in a Language-Model-as-a-Service Framework](https://mlsanity.com/paper/2112.07522/) (2021)
- [Identifying Chinese Opinion Expressions with Extremely-Noisy Crowdsourcing Annotations](https://mlsanity.com/paper/2204.10714/) (2022)
- [Multi-granularity Argument Mining in Legal Texts](https://mlsanity.com/paper/2210.09472/) (2022)
- [Multi-Task Attentive Residual Networks for Argument Mining](https://mlsanity.com/paper/2102.12227/) (2021)
- [Computational Argumentation-based Chatbots: a Survey](https://mlsanity.com/paper/2401.03454/) (2024)
- [Limited Generalizability in Argument Mining: State-Of-The-Art Models Learn Datasets, Not Arguments](https://mlsanity.com/paper/2505.22137/) (2025)
- [Overview of the CLAIMSCAN-2023: Uncovering Truth in Social Media through Claim Detection and Identification of Claim Spans](https://mlsanity.com/paper/2310.19267/) (2023)
- [ArgInstruct: Specialized Instruction Fine-Tuning for Computational Argumentation](https://mlsanity.com/paper/2505.22076/) (2025)
- [Revisiting Active Learning under (Human) Label Variation](https://mlsanity.com/paper/2507.02593/) (2025)
- [Topic Ontologies for Arguments](https://mlsanity.com/paper/2301.09759/) (2023)
- [Towards a Holistic View on Argument Quality Prediction](https://mlsanity.com/paper/2205.09803/) (2022)
- [Prompt, Condition, and Generate: Classification of Unsupported Claims with In-Context Learning](https://mlsanity.com/paper/2309.10359/) (2023)
- [ArgSciChat: A Dataset for Argumentative Dialogues on Scientific Papers](https://mlsanity.com/paper/2202.06690/) (2022)
- [Examining Political Rhetoric with Epistemic Stance Detection](https://mlsanity.com/paper/2212.14486/) (2022)
- [Learning from Sufficient Rationales: Analysing the Relationship Between Explanation Faithfulness and Token-level Regularisation Strategies](https://mlsanity.com/paper/2511.16353/) (2025)
- [Active Learning for Argument Mining: A Practical Approach](https://mlsanity.com/paper/2109.13611/) (2021)
- [Perturbations and Subpopulations for Testing Robustness in Token-Based Argument Unit Recognition](https://mlsanity.com/paper/2209.14780/) (2022)
- [Explainable Topic-Enhanced Argument Mining from Heterogeneous Sources](https://mlsanity.com/paper/2307.12131/) (2023)
- [Detection of fields of applications in biomedical abstracts with the support of argumentation elements](https://mlsanity.com/paper/2404.06121/) (2024)
- [Structured Claim-Level Discourse Representations for Dense Health Narratives](https://mlsanity.com/paper/2609.18905/) (2026)
- [Designing and Analysing Argument Mining Pipelines: Towards a Comprehensive Assessment](https://mlsanity.com/paper/2609.26338/) (2026)

## Abstract (arXiv)

Prior work has commonly defined argument retrieval from heterogeneous document collections as a sentence-level classification task. Consequently, argument retrieval suffers both from low recall and from sentence segmentation errors making it difficult for humans and machines to consume the arguments. In this work, we argue that the task should be performed on a more fine-grained level of sequence labeling. For this, we define the task as Argument Unit Recognition and Classification (AURC). We present a dataset of arguments from heterogeneous sources annotated as spans of tokens within a sentence, as well as with a corresponding stance. We show that and how such difficult argument annotations can be effectively collected through crowdsourcing with high interannotator agreement. The new benchmark, AURC-8, contains up to 15% more arguments per topic as compared to annotations on the sentence level. We identify a number of methods targeted at AURC sequence labeling, achieving close to human performance on known domains. Further analysis also reveals that, contrary to previous approaches, our methods are more robust against sentence segmentation errors. We publicly release our code and the AURC-8 dataset.