Research map / Label-efficient and robust learning / Recognition and long-tail
Jointly Extracting Multiple Triplets with Multilayer Translation Constraints
Zhen Tan, Xiang Zhao, Wei Wang, Weidong Xiao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add relation part (RP) to tri-part tagging (ablation) | TME · NYT-multi (top-2) | F1: 0.486 -> 0.567 | Improved |
| add type part (TP) to tagging scheme (ablation) | TME · NYT-multi (top-2) | F1: 0.561 -> 0.567 | Improved |
| add both TP and RP (full tri-part tagging) (ablation) | TME · NYT-multi (top-2) | F1: 0.470 -> 0.567 | Improved |
| add multi-layer translation (Bi-LSTM layer score functions) over embedding-only (ablation) | TME · NYT-multi (top-2) | F1: 0.433 -> 0.567 | Improved |
| add embedding-layer score function to Bi-LSTM-only translation (ablation) | TME · NYT-multi (top-2) | F1: 0.431 -> 0.567 | Improved |
| add character embedding (ablation) | TME · NYT-multi (top-2) | F1: 0.552 -> 0.567 | Improved |
| add CRF layer (ablation) | TME · NYT-multi (top-2) | F1: 0.530 -> 0.567 | Improved |
| add dropout (ablation) | TME · NYT-multi (top-2) | F1: 0.556 -> 0.567 | Improved |
| add pre-training (ablation) | TME · NYT-multi (top-2) | F1: 0.530 -> 0.567 | Improved |
| use same relation embedding across layers instead of extra embeddings (TME-MR) (ablation) | TME · NYT-multi | F1: 0.507 -> 0.551 | Improved |
| use learned relation embeddings instead of random stable ones (TME-RR) (ablation) | TME · NYT-multi | F1: 0.437 -> 0.551 | Improved |
| add negative sampling (vs TME-NS) (ablation) | TME · NYT-multi | F1: 0.525 -> 0.551 | Improved |
Closest papers by meaning
- Contrastive Triple Extraction with Generative Transformer (AAAI 2021 · similarity 0.87)
- A Boundary Token Graph for Zero-Shot Relation Triplet Extraction Involving Discontinuous Entities (AAAI 2026 · similarity 0.86)
- OneRel: Joint Entity and Relation Extraction with One Module in One Step (AAAI 2022 · similarity 0.86)
- Well-Written Knowledge Graphs: Most Effective RDF Syntaxes for Triple Linearization in End-to-End Extraction of Relations from Texts (Student Abstract) (AAAI 2024 · similarity 0.84)
- An Autoregressive Text-to-Graph Framework for Joint Entity and Relation Extraction (AAAI 2024 · similarity 0.84)
- Knowledge Graph Completion with Relation-Aware Anchor Enhancement (AAAI 2025 · similarity 0.82)
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.
