End-to-End Neural Entity Linking

Entity Linking (EL) is an essential task for semantic text understanding and information extraction. Popular methods separately address the Mention Detection (MD) and Entity Disambiguation (ED) stages of EL, without leveraging their mutual dependency. We here propose the first neural end-to-end EL system that jointly discovers and links entities in a text document. The main idea is to consider all possible spans as potential mentions and learn contextual similarity scores over their entity candidates that are useful for both MD and ED decisions. Key components are context-aware mention embeddings, entity embeddings and a probabilistic mention - entity map, without demanding other engineered features. Empirically, we show that our end-to-end method significantly outperforms popular systems on the Gerbil platform when enough training data is available. Conversely, if testing datasets follow different annotation conventions compared to the training set (e.g. queries/ tweets vs news documents), our ED model coupled with a traditional NER system offers the best or second best EL accuracy.

PDF Abstract CONLL 2018 PDF CONLL 2018 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Entity Linking AIDA-CoNLL Kolitsas et al. (2018) Micro-F1 strong 82.4 # 8
Entity Linking Derczynski Kolitsas et al. (2018) Micro-F1 34.1 # 4
Entity Linking MSNBC Kolitsas et al. (2018) Micro-F1 72.4 # 3
Entity Linking N3-Reuters-128 E2E Micro-F1 54.6 # 2
Entity Linking OKE-2015 E2E Micro-F1 66.9 # 1
Entity Linking OKE-2016 E2E Micro-F1 58.4 # 2

Methods


No methods listed for this paper. Add relevant methods here