mlsanityData to 7 Oct 2026

Multi-Task Attentive Residual Networks for Argument Mining

arXiv 2102.12227 ↗First posted 24 Feb 2021cs.CL cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

We explore the use of residual networks and neural attention for multiple argument mining tasks. We propose a residual architecture that exploits attention, multi-task learning, and makes use of ensemble, without any assumption on document or argument structure. We present an extensive experimental evaluation on five different corpora of user-generated comments, scientific publications, and persuasive essays. Our results show that our approach is a strong competitor against state-of-the-art architectures with a higher computational footprint or corpus-specific design, representing an interesting compromise between generality, performance accuracy and reduced model size.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 38 of its 93 references that are in the map. First posted on arXiv 24 Feb 2021.

Builds on

38 of 93 references.

References · 38

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  5. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  6. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  7. 2016Densely Connected Convolutional Networkscited by 6,691
  8. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  9. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  10. 2018Deep contextualized word representationscited by 2,285
  11. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,935
  12. 2019SciBERT: A Pretrained Language Model for Scientific Textcited by 1,404
26 more
  1. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
  2. 2019Attention is not Explanationcited by 916
  3. 2015Pointer Networkscited by 882
  4. 2020A Primer in BERTology: What we know about how BERT workscited by 807
  5. 2019Attention is not not Explanationcited by 629
  6. 2019Green AIcited by 620
  7. 2019Attention in Natural Language Processingcited by 100
  8. 2016Parsing Argumentation Structures in Persuasive Essayscited by 99
  9. 2017Interactive Attention Networks for Aspect-Level Sentiment Classificationcited by 91
  10. 2017Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Taggingcited by 71
  11. 2016Argumentation Mining in User-Generated Web Discoursecited by 69
  12. 2018Cross-topic Argument Mining from Heterogeneous Sources Using Attention-based Neural Networkscited by 58
  13. 2019Classification and Clustering of Arguments with Contextualized Word Embeddingscited by 57
  14. 2017Neural End-to-End Learning for Computational Argumentation Miningcited by 41
  15. 2017Argument Mining with Structured SVMs and RNNscited by 37
  16. 2016Recurrent Highway Networkscited by 36
  17. 2019Corpus Wide Argument Mining -- a Working Solutioncited by 36
  18. 2019Fine-Grained Argument Unit Recognition and Classificationcited by 26
  19. 2020Modeling Content and Context with Deep Relational Learningcited by 16
  20. 2019The evolution of argumentation mining: From models to social media and emerging toolscited by 9
  21. 2017Deep Residual Learning for Weakly-Supervised Relation Extractioncited by 7
  22. 2019Argumentative Relation Classification as Plausibility Rankingcited by 6
  23. 2019Neural-Symbolic Argumentation Mining: an Argument in Favor of Deep Learning and Reasoningcited by 3
  24. 2021Contextual Argument Component Classification for Class Discussionscited by 3
  25. 2019Is It Worth the Attention? A Comparative Evaluation of Attention Layers for Argument Unit Segmentationcited by 2
  26. 2020"Let's Eat Grandma": Does Punctuation Matter in Sentence Representation?cited by 1

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 1; 2024: 2; 2025: 1.

6 papers.

  1. 2024Natural Language Processing for the Legal Domain: A Survey of Tasks, Datasets, Models, and Challengescited by 42
  2. 2025Large Language Models in Argument Mining: A Surveycited by 14
  3. 2021Tree-Constrained Graph Neural Networks For Argument Miningcited by 2
  4. 2022Enhancing Legal Argument Mining with Domain Pre-training and Neural Networkscited by 2
  5. 2023Cross-Genre Argument Mining: Can Language Models Automatically Fill in Missing Discourse Markers?cited by 1
  6. 2024DMON: A Simple yet Effective Approach for Argument Structure Learningcited by 0