This before That: Causal Precedence in the Biomedical Domain
This work addresses the need for causal mechanisms in biomedical search and inference, but it is incremental as it builds on existing precedence tasks.
The paper tackled the problem of identifying causal precedence in biomedical texts, distinct from temporal precedence, by creating a hand-annotated corpus and evaluating various models, with the best model achieving a micro F1 score of 46 points.
Causal precedence between biochemical interactions is crucial in the biomedical domain, because it transforms collections of individual interactions, e.g., bindings and phosphorylations, into the causal mechanisms needed to inform meaningful search and inference. Here, we analyze causal precedence in the biomedical domain as distinct from open-domain, temporal precedence. First, we describe a novel, hand-annotated text corpus of causal precedence in the biomedical domain. Second, we use this corpus to investigate a battery of models of precedence, covering rule-based, feature-based, and latent representation models. The highest-performing individual model achieved a micro F1 of 43 points, approaching the best performers on the simpler temporal-only precedence tasks. Feature-based and latent representation models each outperform the rule-based models, but their performance is complementary to one another. We apply a sieve-based architecture to capitalize on this lack of overlap, achieving a micro F1 score of 46 points.