Temporal Relation Classification in the clinical domain as a textual entailment task with the Ask2Transformers framework
This repository contains the code for our zero-shot evaluation of A2T textual entailment models on temporal relation classification in clinical narratives.
The textual entailment models are from the Ask2Transformers framework (Sainz, 2021b) and the code is based on the work from Sainz et al. (2021a). The corpus was retrieved from the i2b2 2012 Temporal Relations Task (Sun, 2013).
This poster sums up our work and was presented at the University of the Basque Country (UPV/ EHU) as a final project for the Language Analysis and Processing Master's degree.
Sainz, O., Lopez de Lacalle, O., Labaka, G., Barrena, A., & Agirre, E. (2021a). Label Verbalization and Entailment for Effective Zero and Few-Shot Relation Extraction. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. https://doi.org/10.18653/v1/2021.emnlp-main.92
Sainz, O., & Rigau, G. (2021b). Ask2Transformers: Zero-Shot Domain labelling with Pre-trained Language Models (Version 2). arXiv. https://doi.org/10.48550/ARXIV.2101.02661
Sun, W., Rumshisky, A., & Uzuner, O. (2013). Evaluating temporal relations in clinical text: 2012 i2b2 Challenge. In Journal of the American Medical Informatics Association (Vol. 20, Issue 5, pp. 806–813). Oxford University Press (OUP). https://doi.org/10.1136/amiajnl-2013-001628
ETEREC-A2T is licensed under the CC BY-SA-NC 4.0 license. The text of the license can be found here.