A Search-based Neural Model for Biomedical Nested and Overlapping Event Detection
This addresses the challenge of extracting complex event structures in biomedical literature, which is incremental as it builds on existing methods but improves efficiency and performance.
The authors tackled the problem of detecting nested and overlapping events in biomedical text by proposing a search-based neural network model that treats it as a search on a relation graph, achieving performance comparable to the state-of-the-art TEES system on the BioNLP CG 2013 dataset without using syntactic or hand-engineered features, with analyses showing higher F1-score and computational efficiency.
We tackle the nested and overlapping event detection task and propose a novel search-based neural network (SBNN) structured prediction model that treats the task as a search problem on a relation graph of trigger-argument structures. Unlike existing structured prediction tasks such as dependency parsing, the task targets to detect DAG structures, which constitute events, from the relation graph. We define actions to construct events and use all the beams in a beam search to detect all event structures that may be overlapping and nested. The search process constructs events in a bottom-up manner while modelling the global properties for nested and overlapping structures simultaneously using neural networks. We show that the model achieves performance comparable to the state-of-the-art model Turku Event Extraction System (TEES) on the BioNLP Cancer Genetics (CG) Shared Task 2013 without the use of any syntactic and hand-engineered features. Further analyses on the development set show that our model is more computationally efficient while yielding higher F1-score performance.