Work

JAKET: Joint Pre-training of Knowledge Graph and Language Understanding

Year: 2022
Type: conference-paper
Abstract: Knowledge graphs (KGs) contain rich information about world knowledge, entities, and relations. Thus, they can be great supplements to existing pre-trained language models. However, it remains a challenge to efficiently integrate information from KG into language modeling. And the understanding of a knowledge graph requires related context. We propose a novel joint pre-training framework, JAKET, to model both the knowledge graph and language. The knowledge module and language module provide essential information to mutually assist each other: the knowledge module produces embeddings for entities in text while the language module generates context-aware initial embeddings for entities and relations in the graph. Our design enables the pre-trained model to easily adapt to unseen knowledge graphs in new domains. Experiment results on several knowledge-aware NLP tasks show that our proposed framework achieves superior performance by effectively leveraging knowledge in language understanding.
Language: English
Open Access status: diamond
OpenAlex ID: W3090656107
FWCI: 10.8
Cites: 54
Cited by: 183
Related to: 10