Relation Classification as Two-way Span-Prediction
This improves relation classification for natural language processing tasks, representing an incremental advance.
The paper tackles relation classification by treating it as a span-prediction problem instead of using single embeddings, achieving state-of-the-art results on TACRED and SemEval task 8 datasets.
The current supervised relation classification (RC) task uses a single embedding to represent the relation between a pair of entities. We argue that a better approach is to treat the RC task as span-prediction (SP) problem, similar to Question answering (QA). We present a span-prediction based system for RC and evaluate its performance compared to the embedding based system. We demonstrate that the supervised SP objective works significantly better then the standard classification based objective. We achieve state-of-the-art results on the TACRED and SemEval task 8 datasets.