Journal Article

Dr Michael Stewart

Authors: Michael Stewart, Wei Liu



Knowledge Information Systems

Stewart, M., Liu, W. E2EET: from pipeline to end-to-end entity typing via transformer-based embeddings. Knowl Inf Syst (2021).

Quality Indicators

Peer Reviewed

Q1 Journal as rated in SJR

Relevance to the Centre

T1 are looking at an pipeline based approach to their research. In this paper Michael identifies that existing entity typing models require pre-identified mentions and cannot operate directly on plain text. Pipeline-based approaches are therefore used to join a mention extraction model and an entity typing model to process raw text. Another key limiting factor is that these mention-level ET models are trained on fixed context windows, which makes the entity typing results sensitive to window size selection. In light of these drawbacks, we propose an end-to-end entity typing model (E2EET) using a Bi-GRU to remove the dependency on window size. To demonstrate the effectiveness of our E2EET model, we created a stronger baseline mention-level model by incorporating the latest contextualised transformer-based embeddings (BERT).


Link to Publication