Adversarial training for multi-context joint entity and relation extraction
Adversarial training (AT) is a regularization method that can be used to improve the robustness of neural network methods by adding small perturbations in the training data. We show how to use AT for the tasks of entity recognition and relation extraction. In particular, we demonstrate that applying AT to a general purpose baseline model for jointly extracting entities and relations, allows improving the state-of-the-art effectiveness on several datasets in different contexts (i.e., news, biomedical, and real estate data) and for different languages (English and Dutch).
PDF Abstract EMNLP 2018 PDF EMNLP 2018 AbstractDatasets
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Relation Extraction | ACE 2004 | multi-head + AT | NER Micro F1 | 81.64 | # 8 | |
RE+ Micro F1 | 47.45 | # 7 | ||||
Cross Sentence | No | # 1 | ||||
Relation Extraction | Adverse Drug Events (ADE) Corpus | multi-head + AT | RE+ Macro F1 | 75.52 | # 13 | |
NER Macro F1 | 86.73 | # 12 | ||||
Relation Extraction | CoNLL04 | multi-head + AT | NER Macro F1 | 83.6 | # 7 | |
RE+ Macro F1 | 61.95 | # 8 |