Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
158 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Detection of fields of applications in biomedical abstracts with the support of argumentation elements (2404.06121v1)

Published 9 Apr 2024 in cs.CL

Abstract: Focusing on particular facts, instead of the complete text, can potentially improve searching for specific information in the scientific literature. In particular, argumentative elements allow focusing on specific parts of a publication, e.g., the background section or the claims from the authors. We evaluated some tools for the extraction of argumentation elements for a specific task in biomedicine, namely, for detecting the fields of the application in a biomedical publication, e.g, whether it addresses the problem of disease diagnosis or drug development. We performed experiments with the PubMedBERT pre-trained model, which was fine-tuned on a specific corpus for the task. We compared the use of title and abstract to restricting to only some argumentative elements. The top F1 scores ranged from 0.22 to 0.84, depending on the field of application. The best argumentative labels were the ones related the conclusion and background sections of an abstract.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (33)
  1. Argumentation mining in scientific literature: From computational linguistics to biomedicine. In Proceedings of the BIR 2021: 11th International Workshop on Bibliometric-enhanced Information Retrieval at ECIR 2021, pages 20–36.
  2. Automatic semantic classification of scientific literature according to the hallmarks of cancer. Bioinformatics, 32(3):432–440.
  3. Argument mining as rapid screening tool of covid-19 literature quality: Preliminary evidence. Frontiers in Public Health, 10.
  4. Smafira-c: A benchmark text corpus for evaluation of approaches to relevance ranking and knowledge discovery in the biomedical domain. PREPRINT (Version 1) available at Research Square.
  5. TARGER: Neural argument mining at your fingertips. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 195–200, Florence, Italy. Association for Computational Linguistics.
  6. Advanced non-animal models in biomedical research : respiratory tract diseases. Publications Office of the European Union.
  7. Advanced Non-animal Models in Biomedical Research - Immunogenicity testing for advanced therapy medicinal products. Publications Office of the European Union.
  8. Advanced non-animal models in biomedical research : cardiovascular diseases. Publications Office of the European Union.
  9. Advanced non-animal models in biomedical research : autoimmune diseases. Publications Office of the European Union.
  10. Advanced non-animal models in biomedical research : immuno-oncology. Publications Office of the European Union.
  11. Advanced non-animal models in biomedical research : breast cancer. Publications Office of the European Union.
  12. Advanced non-animal models in biomedical research : neurodegenerative diseases. Publications Office of the European Union.
  13. Argumentation mining in scientific literature for sustainable development. In Proceedings of the 8th Workshop on Argument Mining, pages 100–111, Punta Cana, Dominican Republic. Association for Computational Linguistics.
  14. Domain-specific language model pretraining for biomedical natural language processing. ACM Transactions on Computing for Healthcare, 3(1):1–23.
  15. Eco-collectf: A corpus of annotated evidence-based assertions in biomedical manuscripts. Frontiers in Research Metrics and Analytics, 6.
  16. Hierarchical neural networks for sequential sentence classification in medical scientific abstracts. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3100–3109, Brussels, Belgium. Association for Computational Linguistics.
  17. Dinesh R. Katti and Kalpana S. Katti. 2017. Cancer cell mechanics with altered cytoskeletal behavior and substrate effects: A 3d finite element modeling study. Journal of the Mechanical Behavior of Biomedical Materials, 76:125–134. Structure-Property Relationships in Biological and Bioinspired Materials.
  18. Nucleocytoplasmic distribution of s6k1 depends on the density and motility of mcf-7 cells in vitro [version 2; peer review: 2 approved]. F1000Research, 7(1332).
  19. Text-mining approaches in molecular biology and biomedicine. Drug Discovery Today, 10(6):439–445.
  20. Text mining for improved exposure assessment. PLOS ONE, 12(3):1–21.
  21. ArguminSci: A tool for analyzing argumentation and rhetorical aspects in scientific writing. In Proceedings of the 5th Workshop on Argument Mining, pages 22–28, Brussels, Belgium. Association for Computational Linguistics.
  22. Amica: An argumentative search engine for covid-19 literature. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, pages 5932–5935. International Joint Conferences on Artificial Intelligence Organization. Demo Track.
  23. Marco Lippi and Paolo Torroni. 2016. Margot: A web server for argumentation mining. Expert Systems with Applications, 65:292–303.
  24. BioRED: a rich biomedical relation extraction dataset. Briefings in Bioinformatics, 23(5). Bbac282.
  25. Acta a tool for argumentative clinical trial analysis. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19, pages 6551–6553. International Joint Conferences on Artificial Intelligence Organization.
  26. Covid-on-the-Web: Exploring the COVID-19 scientific literature through visualization of linked data from entity and argument mining. Quantitative Science Studies, 2(4):1301–1323.
  27. A microvascularized tumor-mimetic platform for assessing anti-cancer drug efficacy. Scientific Reports, 8(1):3171.
  28. Bam: Benchmarking argument mining on scientific documents. In The AAAI-22 Workshop on Scientific Document Understanding at the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22). CEUR Workshop Proceedings.
  29. ArgumenText: Searching for arguments in heterogeneous sources. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations, pages 21–25, New Orleans, Louisiana. Association for Computational Linguistics.
  30. Fine-grained argument unit recognition and classification. Thirty-Fourth Aaai Conference on Artificial Intelligence, the Thirty-Second Innovative Applications of Artificial Intelligence Conference and the Tenth Aaai Symposium on Educational Advances in Artificial Intelligence, pages 9048–9056.
  31. Building an argument search engine for the web. In Proceedings of the 4th Workshop on Argument Mining, pages 49–59, Copenhagen, Denmark. Association for Computational Linguistics.
  32. The representation of argumentation in scientific papers: A comparative analysis of two research areas. J. Assoc. Inf. Sci. Technol., 73(6):863–878.
  33. PubTator central: automated concept annotation for biomedical full text articles. Nucleic Acids Research, 47(W1):W587–W593.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now