Bidirectional End-to-End Learning of Retriever-Reader Paradigm for Entity Linking

arXiv:2306.12245v4 Announce Type: replace
Abstract: Entity Linking (EL) is a fundamental task for Information Extraction and Knowledge Graphs. The general form of EL (i.e., end-to-end EL) aims to first find mentions in the given input document and then link the mentions to corresponding entities in a specific knowledge base. Recently, the paradigm of retriever-reader promotes the progress of end-to-end EL, benefiting from the advantages of dense entity retrieval and machine reading comprehension. However, the existing study only trains the retriever …

abstract arxiv cs.cl document extraction form general graphs information information extraction knowledge knowledge base knowledge graphs paradigm reader type