Span-based single-stage joint entity-relation extraction model

Extracting entities and relations from the unstructured text has attracted increasing attention in recent years. The existing work has achieved considerable results, yet it is difficult to solve entity overlap and exposure bias. To address cascading errors, exposure bias, and entity overlap in existing entity relation extraction approaches, we propose a joint entity relation extraction model (SMHS) based on a span-level multi-head selection mechanism, transforming entity relation extraction into a span-level multi-head selection problem. Our model uses span-tagger and span-embedding to construct span semantic vectors, utilizes LSTM and multi-head self-attention mechanism for span feature extraction, multi-head selection mechanism for span-level relation decoding, and introduces span classification task for multi-task learning to decode out the relation triad in a single-stage. Experiments on the classic English dataset NYT and the publicly available Chinese relationship extraction dataset DuIE 2.0 show that this method achieves better results than the baseline method, which verifies the effectiveness of this method. Source code and data are published here.

Automated summary

Extracting entities and relations from unstructured text has gained attention recently. Existing methods have achieved good results but struggle with entity overlap and exposure bias. To address these challenges, we propose a joint entity relation extraction model based on a span-level multi-head selection mechanism. Our model outperforms the baseline method on English dataset NYT and Chinese dataset DuIE 2.0, confirming its effectiveness.