FII SMART at SemEval 2023 Task7: Multi-evidence Natural Language Inference for Clinical Trial Data
Mihai Volosincu, Cosmin Lupu, Diana Trandabat, Daniela Gifu
The 17th International Workshop on Semantic Evaluation (SemEval-2023) Task 7: multi-evidence natural language inference for clinical trial data Paper
TLDR:
The "Multi-evidence Natural Language Inference forClinical Trial Data" task at SemEval 2023competition focuses on extracting essentialinformation on clinical trial data, by posing twosubtasks on textual entailment and evidence retrieval.In the context of SemEval, we present a comparisonbetween a met
You can open the
#paper-SemEval_33
channel in a separate window.
Abstract:
The "Multi-evidence Natural Language Inference forClinical Trial Data" task at SemEval 2023competition focuses on extracting essentialinformation on clinical trial data, by posing twosubtasks on textual entailment and evidence retrieval.In the context of SemEval, we present a comparisonbetween a method based on the BioBERT model anda CNN model. The task is based on a collection ofbreast cancer Clinical Trial Reports (CTRs),statements, explanations, and labels annotated bydomain expert annotators. We achieved F1 scores of0.69 for determining the inference relation(entailment vs contradiction) between CTR -statement pairs. The implementation of our system ismade available via Github - https://github.com/volosincu/FII\_Smart\_\_Semeval2023.