End-to-End Neural Relation Extraction with Global Optimization
Neural networks have shown promising results for relation extraction. State-of-the-art models cast the task as an end-to-end problem, solved incrementally using a local classifier. Yet previous work using statistical models have demonstrated that global optimization can achieve better performances compared to local classification. We build a globally optimized neural model for end-to-end relation extraction, proposing novel LSTM features in order to better learn context representations. In addition, we present a novel method to integrate syntactic information to facilitate global learning, yet requiring little background on syntactic grammars thus being easy to extend. Experimental results show that our proposed model is highly effective, achieving the best performances on two standard benchmarks.
PDF AbstractResults 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 | Global | NER Micro F1 | 83.6 | # 16 | |
RE+ Micro F1 | 57.5 | # 12 | ||||
Sentence Encoder | biLSTM | # 1 | ||||
Cross Sentence | No | # 1 | ||||
Relation Extraction | CoNLL04 | Global | RE+ Micro F1 | 67.8 | # 10 | |
NER Micro F1 | 85.6 | # 8 |