EMNLP Findings2020
Biomedical Event Extraction on Graph Edge-conditioned Attention Networks with Hierarchical Knowledge Graphs
Kung-Hsiang Huang, Mu Yang, Nanyun Peng
Abstract
Biomedical event extraction is critical in understanding biomolecular interactions described in scientific corpus. One of the main challenges is to identify nested structured events that are associated with non-indicative trigger words. We propose to incorporate domain knowledge from Unified Medical Language System (UMLS) to a pre-trained language model via a hierarchical graph representation encoded by a proposed Graph Edgeconditioned Attention Networks (GEANet). To better recognize the trigger words, each sentence is first grounded to a sentence graph based on a jointly modeled hierarchical knowledge graph from UMLS. The grounded graphs are then propagated by GEANet, a novel graph neural networks for enhanced capabilities in inferring complex events. On BioNLP 2011 GENIA Event Extraction task, our approach achieved 1.41% F 1 and 3.19% F 1 improvements on all events and complex events, respectively. Ablation studies confirm the importance of GEANet and hierarchical KG.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
4 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- DICE: Data-Efficient Clinical Event Extraction with Generative Models cites A Joint Neural Model for Information Extraction with Global Features
- SciEvent: Benchmarking Multi-domain Scientific Event Extraction cites A Joint Neural Model for Information Extraction with Global Features
- Joint Biomedical Entity and Relation Extraction with Knowledge-Enhanced Collective Inference cites A Joint Neural Model for Information Extraction with Global Features
Cited by top-tier papers4
- DICE: Data-Efficient Clinical Event Extraction with Generative ModelsMingyu Derek Ma, Alexander Taylor, Wei Wang, Nanyun PengACL 2023 · 18 citations
- SciEvent: Benchmarking Multi-domain Scientific Event ExtractionBofu Dong, Pritesh Shah, Sumedh Sonawane, Tiyasha Banerjee et al.EMNLP 2025
- Joint Biomedical Entity and Relation Extraction with Knowledge-Enhanced Collective InferenceTuan Manh Lai, Heng Ji, ChengXiang Zhai, Quan Hung TranACL 2021
- Fine-grained Information Extraction from Biomedical Literature based on Knowledge-enriched Abstract Meaning RepresentationZixuan Zhang, Nikolaus Nova Parulian, Heng Ji, Ahmed Elsayed et al.ACL 2021
Builds on1
Related papers
- Integrating Graph Contextualized Knowledge into Pre-trained Language ModelsBin He, Di Zhou, Jinghui Xiao, Xin Jiang et al.EMNLP Findings 2020 · 92 citations
- BALI: Enhancing Biomedical Language Representations through Knowledge Graph and Language Model AlignmentAndrey Sakhovskiy, Elena TutubalinaSIGIR 2025 · 2 citations
- Hierarchical Attention Propagation for Healthcare Representation LearningMuhan Zhang, Christopher Ryan King, Michael Avidan, Yixin ChenKDD 2020 · 44 citations
- GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge GraphsPengcheng Jiang, Cao Xiao, Adam Cross, Jimeng SunICLR 2024 · 77 citations
- Learning Conceptual-Contextual Embeddings for Medical TextXiao Zhang, Dejing Dou, Ji WuAAAI 2020 · 17 citations
