LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention

Citations Over TimeTop 1% of 2020 papers

Abstract

Entity representations are useful in natural language tasks involving entities. In this paper, we propose new pretrained contextualized representations of words and entities based on the bidirectional transformer The proposed model treats words and entities in a given text as independent tokens, and outputs contextualized representations of them. Our model is trained using a new pretraining task based on the masked language model of BERT (Devlin et al., 2019). The task involves predicting randomly masked words and entities in a large entity-annotated corpus retrieved from Wikipedia. We also propose an entity-aware self-attention mechanism that is an extension of the self-attention mechanism of the transformer, and considers the types of tokens (words or entities) when computing attention scores. The proposed model achieves impressive empirical performance on a wide range of entity-related tasks. In particular, it obtains state-of-the-art results on five well-known datasets: Open Entity (entity typing), TACRED (relation classification), CoNLL-2003 (named entity recognition), ReCoRD (cloze-style question answering), and SQuAD 1.1 (extractive question answering). Our source code and pretrained representations are available at

Related Papers

• → A literature review of question answering system using Named Entity Recognition(2016)13 cited
• NERU: Named Entity Recognition for German(2014)
• → Improving named entity recognition and disambiguation in news headlines(2019)1 cited
• → Analysis of named entity recognition & entity linking in historical text(2016)1 cited