Medical Argument Mining: Exploitation of Scarce Data Using NLI Systems

• Autores: Maitane Urruela, Sergio Martín, Iker de la Iglesia, Ander Barrena Madinabeitia
• Localización: Procesamiento del lenguaje natural, ISSN 1135-5948, Nº. 75, 2025 (Ejemplar dedicado a: Procesamiento del Lenguaje Natural, Revista nº 75, septiembre de 2025), págs. 251-262
• Idioma: inglés
• Títulos paralelos:
  • Minería de Argumentos Médicos: Explotación de Datos Escasos Mediante Sistemas NLI
• Enlaces
  • Texto completo
• Resumen
  • español

    Este trabajo presenta un proceso de Minería de Argumentos que extrae entidades argumentativas de textos clínicos e identifica sus relaciones argumentativas utilizando técnicas de clasificación de tokens e Inferencia del Lenguaje Natural. En comparación con otros métodos como la clasificación de texto, esta metodología muestra mejor rendimiento en contextos con escasez de datos. Al evaluar la eficacia de estos métodos en la identificación de estructuras argumentativas que apoyan o refutan posibles diagnósticos, esta investigación sienta las bases para futuras herramientas que puedan proporcionar justificaciones basadas en pruebas para conclusiones clínicas generadas automáticamente.

  • English

    This work presents an Argument Mining process that extracts argumentative entities from clinical texts and identifies their relationships using token classification and Natural Language Inference techniques. Compared to straightforward methods like text classification, this methodology demonstrates superior performance in data-scarce settings. By assessing the effectiveness of these methods in identifying argumentative structures that support or refute possible diagnoses, this research lays the groundwork for future tools that can provide evidence-based justifications for machine-generated clinical conclusions.

• Referencias bibliográficas
  • Bar-Haim, R., I. Bhattacharya, F. Dinuzzo, A. Saha, and N. Slonim. 2017. Stance classification of context-dependent claims. In Proceedings...
  • Cabrio, E. and S. Villata. 2013. A natural language bipolar argumentation approach to support users in online debate interactions. Argument...
  • Daxenberger, J., S. Eger, I. Habernal, C. Stab, and I. Gurevych. 2017. What is the essence of a claim? cross-domain claim identification....
  • De la Iglesia, I., A. Atutxa, K. Gojenola, and A. Barrena. 2023. EriBERTa: A Bilingual Pre-Trained Language Model for Clinical Natural Language...
  • Duthie, R., K. Budzynska, and C. Reed. 2016. Mining ethos in political debate. In Computational Models of Argument. IOS Press, pages 299–310.
  • Eger, S., J. Daxenberger, and I. Gurevych. 2017. Neural end-to-end learning for computational argumentation mining. arXiv preprint arXiv:1704.06104.
  • Fellbaum, C. et al. 1998. Wordnet: An electronic lexical database mit press. Cambridge, Massachusetts.
  • Habernal, I. and I. Gurevych. 2017. Argumentation mining in user-generated web discourse. Computational linguistics, 43(1):125–179.
  • Laurer, M., W. v. Atteveldt, A. S. Casas, and K. Welbers. 2022. Less Annotating, More Classifying – Addressing the Data Scarcity Issue of...
  • Levy, R., Y. Bilu, D. Hershcovich, E. Aharoni, and N. Slonim. 2014. Context dependent claim detection. In Proceedings of COLING 2014, the...
  • Liu, Y., M. Ott, N. Goyal, J. Du, M. Joshi, D. Chen, O. Levy, M. Lewis, L. Zettlemoyer, and V. Stoyanov. 2019. RoBERTa: A Robustly Optimized...
  • Marro, S., T. A. Collias, E. Cabrio, and S. Villata. 2023. On the automatic assessment of natural language expert explanations in medicine....
  • Mayer, T., E. Cabrio, and S. Villata. 2020. Transformer-based argument mining for healthcare applications. In ECAI 2020. IOS Press, pages...
  • Mayer, T., S. Marro, E. Cabrio, and S. Villata. 2021. Enhancing evidence-based medicine with natural language argumentative analysis of clinical...
  • Nguyen, H. and D. Litman. 2018. Argument mining for improving the automated scoring of persuasive essays. In Proceedings of the AAAI Conference...
  • Piriyatamwong, P., S. Kalloori, and F. Zünd. 2024. Unified argument retrieval system from german news articles using large language models....
  • Rinott, R., L. Dankin, C. Alzate, M. M. Khapra, E. Aharoni, and N. Slonim. 2015. Show me your evidence-an automatic method for context dependent...
  • Sainz, O., I. Gonzalez-Dios, O. Lopez de Lacalle, B. Min, and E. Agirre. 2022. Textual entailment for event argument extraction: Zero- and...
  • Sainz, O. and G. Rigau. 2021. Ask2Transformers: Zero-shot domain labelling with pre-trained language models. arXiv preprint arXiv:2101.02661.
  • Stylianou, N. and I. Vlahavas. 2021. Transformed: End-to-end transformers for evidence-based medicine and argument mining in medical literature....
  • Sviridova, E., A. Yeginbergen, A. Estarrona, E. Cabrio, S. Villata, and R. Agerri. 2024. CasiMedicos-Arg: A Medical Question Answering Dataset...
  • Teufel, S., A. Siddharthan, and C. Batchelor. 2009. Towards domain-independent argumentative zoning: Evidence from chemistry and computational...