Deep Learning for Character-Based Information Extraction

摘要: In this paper we introduce a deep neural network architecture to perform information extraction on character-based sequences, e.g. named-entity recognition Chinese text or secondary-structure detection protein sequences. With task-independent architecture, the relies only simple features, which obviates need for task-specific feature engineering. The proposed discriminative framework includes three important strategies, 1 learning module mapping characters vector representations is included capture semantic relationship between characters; 2 abundant online sequences unlabeled are utilized improve representation through semi-supervised learning; and 3 constraints of spatial dependency among output labels modeled explicitly in architecture. experiments four benchmark datasets have demonstrated that, consistently leads state-of-the-art performance.