Neural Networks Models for Entity Discovery and Linking
This work addresses entity linking for multilingual knowledge base population, but it is incremental as it builds on existing neural methods for a specific contest.
The paper tackled entity discovery and linking in a trilingual setting by developing systems using conditional RNNLM and attention-based encoder-decoder for mention detection, and a neural ranking model for entity linking, achieving an F1 score of 0.624 in end-to-end evaluation.
This paper describes the USTC_NELSLIP systems submitted to the Trilingual Entity Detection and Linking (EDL) track in 2016 TAC Knowledge Base Population (KBP) contests. We have built two systems for entity discovery and mention detection (MD): one uses the conditional RNNLM and the other one uses the attention-based encoder-decoder framework. The entity linking (EL) system consists of two modules: a rule based candidate generation and a neural networks probability ranking model. Moreover, some simple string matching rules are used for NIL clustering. At the end, our best system has achieved an F1 score of 0.624 in the end-to-end typed mention ceaf plus metric.