Adversarial training for multi-context joint entity and relation extraction
TL
TL;DR
Adversarial training is demonstrated to be a regularization method that 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).
Abstract
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).
References30 items
1
Joint entity recognition and relation extraction as a multi-head selection problem
2
Robust Multilingual Part-of-Speech Tagging via Adversarial Training
3
An attentive neural architecture for joint segmentation and parsing and its application to real estate ads
4
Joint entity and relation extraction based on a hybrid neural network
5