BED: Bi-Encoder-Decoder Model for Canonical Relation Extraction
This work addresses a domain-specific issue in natural language processing for relation extraction, offering incremental improvements by enhancing entity representation and generalization to novel entities.
The paper tackles the problem of canonical relation extraction by proposing the Bi-Encoder-Decoder (BED) model to better utilize entity information and handle novel entities, achieving significant performance improvements over previous state-of-the-art methods on two datasets.
Canonical relation extraction aims to extract relational triples from sentences, where the triple elements (entity pairs and their relationship) are mapped to the knowledge base. Recently, methods based on the encoder-decoder architecture are proposed and achieve promising results. However, these methods cannot well utilize the entity information, which is merely used as augmented training data. Moreover, they are incapable of representing novel entities, since no embeddings have been learned for them. In this paper, we propose a novel framework, Bi-Encoder-Decoder (BED), to solve the above issues. Specifically, to fully utilize entity information, we employ an encoder to encode semantics of this information, leading to high-quality entity representations. For novel entities, given a trained entity encoder, their representations can be easily generated. Experimental results on two datasets show that, our method achieves a significant performance improvement over the previous state-of-the-art and handle novel entities well without retraining.