Log In Sign Up

Adversarial training for multi-context joint entity and relation extraction

by   Giannis Bekoulis, et al.

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).


page 1

page 2

page 3

page 4


Joint entity recognition and relation extraction as a multi-head selection problem

State-of-the-art models for joint entity recognition and relation extrac...

Techniques for Jointly Extracting Entities and Relations: A Survey

Relation Extraction is an important task in Information Extraction which...

Joint Learning-based Causal Relation Extraction from Biomedical Literature

Causal relation extraction of biomedical entities is one of the most com...

Adversarial Learning for Supervised and Semi-supervised Relation Extraction in Biomedical Literature

Adversarial training is a technique of improving model performance by in...

Matching the Blanks: Distributional Similarity for Relation Learning

General purpose relation extractors, which can model arbitrary relations...

Improving Performance of Relation Extraction Algorithm via Leveled Adversarial PCNN and Database Expansion

This study introduces database expansion using the Minimum Description L...

Empower Distantly Supervised Relation Extraction with Collaborative Adversarial Training

With recent advances in distantly supervised (DS) relation extraction (R...