Entity Identification as Multitasking

by   Karl Stratos, et al.
Toyota Technological Institute at Chicago

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.


page 1

page 2

page 3

page 4


Label Noise Reduction in Entity Typing by Heterogeneous Partial-Label Embedding

Current systems of fine-grained entity typing use distant supervision in...

Hierarchical Entity Typing via Multi-level Learning to Rank

We propose a novel method for hierarchical entity classification that em...

Modeling Fine-Grained Entity Types with Box Embeddings

Neural entity typing models typically represent entity types as vectors ...

CORE: A Knowledge Graph Entity Type Prediction Method via Complex Space Regression and Embedding

Entity type prediction is an important problem in knowledge graph (KG) r...

Using Type Information to Improve Entity Coreference Resolution

Coreference resolution (CR) is an essential part of discourse analysis. ...

Transformer-based Entity Typing in Knowledge Graphs

We investigate the knowledge graph entity typing task which aims at infe...

Automated Concatenation of Embeddings for Structured Prediction

Pretrained contextualized embeddings are powerful word representations f...

Please sign up or login with your details

Forgot password? Click here to reset