It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers
This work addresses the need for explainable AI in natural language processing, specifically for relation extraction, though it is incremental in combining existing multitask and rule-based techniques.
The paper tackles the tension between generalization and explainability in relation extraction by proposing a multitask learning approach that jointly trains a relation classifier and a sequence model for explanation labeling, showing that joint training generally improves classifier performance and the generated rules enhance rule-based systems.
We propose an explainable approach for relation extraction that mitigates the tension between generalization and explainability by jointly training for the two goals. Our approach uses a multi-task learning architecture, which jointly trains a classifier for relation extraction, and a sequence model that labels words in the context of the relation that explain the decisions of the relation classifier. We also convert the model outputs to rules to bring global explanations to this approach. This sequence model is trained using a hybrid strategy: supervised, when supervision from pre-existing patterns is available, and semi-supervised otherwise. In the latter situation, we treat the sequence model's labels as latent variables, and learn the best assignment that maximizes the performance of the relation classifier. We evaluate the proposed approach on the two datasets and show that the sequence model provides labels that serve as accurate explanations for the relation classifier's decisions, and, importantly, that the joint training generally improves the performance of the relation classifier. We also evaluate the performance of the generated rules and show that the new rules are great add-on to the manual rules and bring the rule-based system much closer to the neural models.