mlsanityData to 7 Oct 2026

Cross-topic Argument Mining from Heterogeneous Sources Using Attention-based Neural Networks

arXiv 1802.05758 ↗First posted 15 Feb 2018cs.CLcited by 58

Not on the map. Why?

Abstract (arXiv)

Argument mining is a core technology for automating argument search in large document collections. Despite its usefulness for this task, most current approaches to argument mining are designed for use only with specific text types and fall short when applied to heterogeneous texts. In this paper, we propose a new sentential annotation scheme that is reliably applicable by crowd workers to arbitrary Web texts. We source annotations for over 25,000 instances covering eight controversial topics. The results of cross-topic experiments show that our attention-based neural network generalizes best to unseen topics and outperforms vanilla BiLSTM models by 6% in accuracy and 11% in F-score.

Key facts. Cited by 58 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 9; 2023: 8; 2024: 14; 2025: 6; 2026: 6.

58 papers.

Sort:

By area:

  1. 2021An Empirical Investigation of the Role of Pre-training in Lifelong Learningcited by 134
  2. 2021Cross-Domain Label-Adaptive Stance Detectioncited by 30
  3. 2024Can Large Language Models perform Relation-based Argument Mining?cited by 23
  4. 2021NewsClaims: A New Benchmark for Claim Detection from News with Attribute Knowledgecited by 20
  5. 2021Claim Detection in Biomedical Twitter Postscited by 18
  6. 2021Classifying Argumentative Relations Using Logical Mechanisms and Argumentation Schemescited by 17
  7. 2021Scientia Potentia Est -- On the Role of Knowledge in Computational Argumentationcited by 17
  8. 2024On Zero-Shot Counterspeech Generation by LLMscited by 17
  9. 2022ImageArg: A Multi-modal Tweet Dataset for Image Persuasiveness Miningcited by 12
  10. 2023Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generationcited by 12
  11. 2024Can Large Language Models Address Open-Target Stance Detection?cited by 10
  12. 2021Multilingual Counter Narrative Type Classificationcited by 9
38 more
  1. 2021Is Stance Detection Topic-Independent and Cross-topic Generalizable? -- A Reproduction Studycited by 9
  2. 2022Few-Shot Stance Detection via Target-Aware Prompt Distillationcited by 9
  3. 2021SciClops: Detecting and Contextualizing Scientific Claims for Assisting Manual Fact-Checkingcited by 8
  4. 2023ArgU: A Controllable Factual Argument Generatorcited by 7
  5. 2021Multi-Task Attentive Residual Networks for Argument Miningcited by 6
  6. 2022Contextual information integration for stance detection via cross-attentioncited by 6
  7. 2024Dive into the Chasm: Probing the Gap between In- and Cross-Topic Generalizationcited by 6
  8. 2024A Hybrid Intelligence Method for Argument Miningcited by 6
  9. 2023Shaping Political Discourse using multi-source News Summarizationcited by 5
  10. 2024Efficient argument classification with compact language models and ChatGPT-4 refinementscited by 5
  11. 2024CrowdCounter: A benchmark type-specific multi-target counterspeech datasetcited by 5
  12. 2025Limited Generalizability in Argument Mining: State-Of-The-Art Models Learn Datasets, Not Argumentscited by 5
  13. 2022Diversity Over Size: On the Effect of Sample and Topic Sizes for Topic-Dependent Argument Mining Datasetscited by 4
  14. 2023Topic-Guided Sampling For Data-Efficient Multi-Domain Stance Detectioncited by 4
  15. 2023How to Handle Different Types of Out-of-Distribution Scenarios in Computational Argumentation? A Comprehensive and Fine-Grained Field Studycited by 4
  16. 2023Overview of ImageArg-2023: The First Shared Task in Multimodal Argument Miningcited by 4
  17. 2024How Hard is this Test Set? NLI Characterization by Exploiting Training Dynamicscited by 4
  18. 2025ArgInstruct: Specialized Instruction Fine-Tuning for Computational Argumentationcited by 4
  19. 2021Focusing Knowledge-based Graph Argument Mining via Topic Modelingcited by 3
  20. 2022Investigating User Radicalization: A Novel Dataset for Identifying Fine-Grained Temporal Shifts in Opinioncited by 3
  21. 2025MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderationcited by 3
  22. 2021Multi-Task and Multi-Corpora Training Strategies to Enhance Argumentative Sentence Linking Performancecited by 2
  23. 2021Tree-Constrained Graph Neural Networks For Argument Miningcited by 2
  24. 2022Towards a Holistic View on Argument Quality Predictioncited by 2
  25. 2023Prompt, Condition, and Generate: Classification of Unsupported Claims with In-Context Learningcited by 2
  26. 2024WIBA: What Is Being Argued? A Comprehensive Approach to Argument Miningcited by 2
  27. 2024Relative Counterfactual Contrastive Learning for Mitigating Pretrained Stance Bias in Stance Detectioncited by 2
  28. 2022A Cascade Model for Argument Mining in Japanese Political Discussions: the QA Lab-PoliInfo-3 Case Studycited by 1
  29. 2024TACO -- Twitter Arguments from COnversationscited by 1
  30. 2024Investigating the Robustness of Modelling Decisions for Few-Shot Cross-Topic Stance Detection: A Preregistered Studycited by 1
  31. 2024CoSD: Collaborative Stance Detection with Contrastive Heterogeneous Topic Graph Learningcited by 1
  32. 2024PerSphere: A Comprehensive Framework for Multi-Faceted Perspective Retrieval and Summarizationcited by 1
  33. 2025A comprehensive study of LLM-based argument classification: from LLAMA through GPT-4o to Deepseek-R1cited by 1
  34. 2025Stakeholder Suite: A Unified AI Framework for Mapping Actors, Topics and Arguments in Public Debatescited by 1
  35. 2026A comprehensive study of LLM-based argument classification: from Llama through DeepSeek to GPT-5.2cited by 1
  36. 2026ArgBench: Benchmarking LLMs on Computational Argumentation Taskscited by 1
  37. 2026AI-Mediated Communication Can Steer Collective Opinioncited by 1
  38. 2021Written Justifications are Key to Aggregate Crowdsourced Forecastscited by 0

50 most cited of 58 All 58 (JSON)