BiSPN: Generating Entity Set and Relation Set Coherently in One Pass
Submission Type: Regular Long Paper
Submission Track: Information Extraction
Keywords: Information Extraction, Joint Entity-Relation Extraction, Non-autoregressive Generation
TL;DR: We propose a novel joint extraction model that can generate entity set and relation set in one pass, which is equipped with two special loss functions to maintain the coherence of generated sets.
Abstract: By modeling the interaction among instances and avoiding error propagation, Set Prediction Networks (SPNs) achieve state-of-the-art performance on the tasks of named entity recognition and relation triple extraction respectively. However, how to jointly extract entities and relation triples via SPNs remains an unexplored problem, where the main challenge is the maintenance of coherence between the predicted entity/relation sets during one-pass generation. In this work, we present Bipartite Set Prediction Network (BiSPN), a novel joint entity-relation extraction model that can efficiently generate entity set and relation set in parallel. To overcome the challenge of coherence, BiSPN is equipped with a novel bipartite consistency loss as well as an entity-relation linking loss during training. Experiments on three biomedical/clinical datasets and a general-domain dataset show that BiSPN achieves new state of the art in knowledge-intensive scene and performs competitively in general-domain, while being more efficient than two-stage joint extraction methods.
Submission Number: 497
Loading