Neural Networks Models for Entity Discovery and Linking

Abstract

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.

9 pages, 5 figures

References in corpus (2)

• ADADELTA: An Adaptive Learning Rate Method
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches

Cited by in corpus (6)

• A General FOFE-net Framework for Simple and Effective Question Answering over Knowledge Bases
• Controllable Text Simplification with Explicit Paraphrasing
• Content based News Recommendation via Shortest Entity Distance over Knowledge Graphs
• A Multi-task Learning Approach for Named Entity Recognition using Local Detection
• Learning Syntactic Dense Embedding with Correlation Graph for Automatic Readability Assessment
• A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification