A Multi-Gate Encoder for Joint Entity and Relation Extraction
“Named entity recognition and relation extraction are core sub-tasks of relational triple extraction. Recent studies have used parameter sharing or joint decoding to create interaction between these two tasks. However, ensuring the specificity of task-specific traits while the two tasks interact properly is a huge difficulty. We propose a multi-gate encoder that models bidirectional task interaction while keeping sufficient feature specificity based on gating mechanism in this paper. Precisely, we design two types of independent gates: task gates to generate task-specific features and interaction gates to generate instructive features to guide the opposite task. Our experiments show that our method increases the state-of-the-art (SOTA) relation F1 scores on ACE04, ACE05 and SciERC datasets to 63.8% (+1.3%), 68.2% (+1.4%), 39.4% (+1.0%), respectively, with higher inference speed over previous SOTA model.”
PDF Abstract
SciERC
ACE 2005
Results from the Paper
Ranked #1 on
Relation Extraction
on ACE 2005
(Sentence Encoder metric)
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Relation Extraction | ACE 2005 | MGE | NER Micro F1 | 89.7 | # 4 | |
| RE+ Micro F1 | 68.2 | # 3 | ||||
| Sentence Encoder | ALBERT | # 1 | ||||
| Cross Sentence | No | # 1 | ||||
| Joint Entity and Relation Extraction | SciERC | MGE | Entity F1 | 68.4 | # 7 | |
| RE+ Micro F1 | 39.4 | # 3 | ||||
| Cross Sentence | No | # 1 |
