Research map / Large language models / Language, safety and interpretability
Jointly Extracting Event Triggers and Arguments by Dependency-Bridge RNN and Tensor-Based Argument Interaction
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| dbRNN vs JRNN | event extraction · ACE 2005 (gold entities) | argument role F1: 55.4 -> 58.7 | Helped |
| add binary dependency bridges to BiLSTM (ablation) | dbRNN · ACE 2005 | trigger id+cl F1: 69.0 -> 71.2 | Helped |
| make dependency bridge weights typed and trainable instead of binary (ablation) | dbRNN · ACE 2005 | argument id+cl F1: 56.8 -> 57.2 | Helped |
| add tensor layer for argument interaction (ablation) | dbRNN · ACE 2005 | argument id F1: 58.2 -> 67.7 | Helped |
| add tensor layer for argument interaction (ablation) | dbRNN · ACE 2005 | argument role F1: 53.1 -> 58.7 | Helped |
| add self-matching attention (ablation) | dbRNN · ACE 2005 | argument role F1: 56.0 -> 58.7 | Helped |
| add max-pooled interaction features (ablation) | dbRNN · ACE 2005 | argument role F1: 55.2 -> 58.7 | Helped |
| add tensor layer, sentences with a single entity (1/1) (ablation) | dbRNN · ACE 2005 1/1 sentences | argument role F1: 54.9 -> 54.6 | No clear effect |
Closest papers by meaning
- Graph Convolutional Networks With Argument-Aware Pooling for Event Detection (AAAI 2018 · similarity 0.87)
- TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency (ICLR 2017 · similarity 0.86)
- Dependency Structure-Enhanced Graph Attention Networks for Event Detection (AAAI 2024 · similarity 0.85)
- Is a Large Language Model a Good Annotator for Event Extraction? (AAAI 2024 · similarity 0.84)
- A Tensor Decomposition Perspective on Second-order RNNs (ICML 2024 · similarity 0.84)
- A Joint Framework with Heterogeneous-Relation-Aware Graph and Multi-Channel Label Enhancing Strategy for Event Causality Extraction (AAAI 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.