Drug Combinations Dataset

AI2 Israel • 2022
Combination therapies have become the standard of care for diseases such as cancer, tuberculosis, malaria and HIV. However, the combinatorial set of available multi-drug treatments creates a challenge in identifying effective combination therapies available in a situation. To assist medical professionals in identifying beneficial drug-combinations, we construct an expert-annotated dataset (consisting 1634 abstracts) for extracting information about the efficacy of drug combinations from the scientific literature. Beyond its practical utility, the dataset also presents a unique NLP challenge, as the first relation extraction dataset consisting of variable-length relations. Furthermore, the relations in this dataset predominantly require language understanding beyond the sentence level, adding to the challenge of this task. We provide a promising baseline model (see the paper/repo) and identify clear areas for further improvement.
License: See Repo


Top Public Submissions
Vijay Viswanathan from the Language Technologies Institute - Carnegie Mellon University, Hillel Taub-Tabib from AI2, Tom Hope AI2 and from the School of Computer Science & Engineering - The Hebrew University of Jerusalem, Yoav Goldberg from AI2 and from the Computer Science Department - Bar Ilan University


Aryeh Tiktinsky, Vijay Viswanathan, Danna Niezni, Dana Azagury, Yosi Shamay, Hillel Taub-Tabib, Tom Hope, Yoav Goldberg