Entity Identification as Multitasking
This work addresses entity identification for NLP researchers by offering a more efficient and scalable method, though it appears incremental as it builds on existing neural models.
The paper tackled the problem of entity identification by proposing a novel neural architecture that frames it as multitasking, separating boundary detection and type prediction to address runtime complexity and lack of segment-level representation issues, resulting in competitive performance with linear scaling in the number of types.
Standard approaches in entity identification hard-code boundary detection and type prediction into labels (e.g., John/B-PER Smith/I-PER) and then perform Viterbi. This has two disadvantages: 1. the runtime complexity grows quadratically in the number of types, and 2. there is no natural segment-level representation. In this paper, we propose a novel neural architecture that addresses these disadvantages. We frame the problem as multitasking, separating boundary detection and type prediction but optimizing them jointly. Despite its simplicity, this architecture performs competitively with fully structured models such as BiLSTM-CRFs while scaling linearly in the number of types. Furthermore, by construction, the model induces type-disambiguating embeddings of predicted mentions.