Relation of the Relations: A New Paradigm of the Relation Extraction Problem
This work addresses the problem of inefficient and incomplete relation extraction in natural language processing for researchers and practitioners, offering a novel approach that is not incremental.
The paper tackles the limitation of traditional relation extraction by proposing a new paradigm that considers all relations in a context simultaneously, addressing interdependencies and quadratic computation time. It achieves improvements of +1.12% on ACE05 and +2.55% on SemEval 2018 Task 7.2 over state-of-the-art methods.
In natural language, often multiple entities appear in the same text. However, most previous works in Relation Extraction (RE) limit the scope to identifying the relation between two entities at a time. Such an approach induces a quadratic computation time, and also overlooks the interdependency between multiple relations, namely the relation of relations (RoR). Due to the significance of RoR in existing datasets, we propose a new paradigm of RE that considers as a whole the predictions of all relations in the same context. Accordingly, we develop a data-driven approach that does not require hand-crafted rules but learns by itself the RoR, using Graph Neural Networks and a relation matrix transformer. Experiments show that our model outperforms the state-of-the-art approaches by +1.12\% on the ACE05 dataset and +2.55\% on SemEval 2018 Task 7.2, which is a substantial improvement on the two competitive benchmarks.