Entity Identification as Multitasking

TL;DR

This paper introduces a multitasking neural architecture for entity identification that separates boundary detection and type prediction, achieving linear scaling and producing type-disambiguating embeddings, thus improving efficiency and interpretability.

Contribution

It proposes a novel neural model that jointly optimizes boundary detection and type prediction as separate tasks, addressing quadratic complexity and lack of segment-level representation.

Findings

Performs competitively with BiLSTM-CRFs

Scales linearly with number of types

Induces type-disambiguating mention embeddings

Abstract

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.