NCUEE-NLP at SemEval-2023 Task 7: Ensemble Biomedical LinkBERT Transformers in Multi-evidence Natural Language Inference for Clinical Trial Data

Chao-Yi Chen, Kao-Yuan Tien, Yuan-Hao Cheng, Lung-Hao Lee

Abstract
This study describes the model design of the NCUEE-NLP system for the SemEval-2023 NLI4CT task that focuses on multi-evidence natural language inference for clinical trial data. We use the LinkBERT transformer in the biomedical domain (denoted as BioLinkBERT) as our main system architecture. First, a set of sentences in clinical trial reports is extracted as evidence for premise-statement inference. This identified evidence is then used to determine the inference relation (i.e., entailment or contradiction). Finally, a soft voting ensemble mechanism is applied to enhance the system performance. For Subtask 1 on textual entailment, our best submission had an F1-score of 0.7091, ranking sixth among all 30 participating teams. For Subtask 2 on evidence retrieval, our best result obtained an F1-score of 0.7940, ranking ninth of 19 submissions.
Anthology ID:
2023.semeval-1.107
Volume:
Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Atul Kr. Ojha, A. Seza Doğruöz, Giovanni Da San Martino, Harish Tayyar Madabushi, Ritesh Kumar, Elisa Sartori
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
776–781
Language:
URL:
https://aclanthology.org/2023.semeval-1.107
DOI:
10.18653/v1/2023.semeval-1.107
Bibkey:
Cite (ACL):
Chao-Yi Chen, Kao-Yuan Tien, Yuan-Hao Cheng, and Lung-Hao Lee. 2023. NCUEE-NLP at SemEval-2023 Task 7: Ensemble Biomedical LinkBERT Transformers in Multi-evidence Natural Language Inference for Clinical Trial Data. In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 776–781, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
NCUEE-NLP at SemEval-2023 Task 7: Ensemble Biomedical LinkBERT Transformers in Multi-evidence Natural Language Inference for Clinical Trial Data (Chen et al., SemEval 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2023.semeval-1.107.pdf
PDF Search