Named Entity Recognition with stack residual LSTM and trainable bias decoding

Abstract

Recurrent Neural Network models are the state-of-the-art for Named Entity Recognition (NER). We present two innovations to improve the performance of these models. The first innovation is the introduction of residual connections between the Stacked Recurrent Neural Network model to address the degradation problem of deep neural networks. The second innovation is a bias decoding mechanism that allows the trained system to adapt to non-differentiable and externally computed objectives, such as the entity-based F-measure. Our work improves the state-of-the-art results for both Spanish and English languages on the standard train/development/test split of the CoNLL 2003 Shared Task NER dataset.

References in corpus (6)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• Exploring the Limits of Language Modeling
• Multi-Task Cross-Lingual Sequence Tagging from Scratch
• Recurrent Convolutional Neural Networks for Discourse Compositionality
• Trainable Greedy Decoding for Neural Machine Translation

Cited by in corpus (6)

• Robust Lexical Features for Improved Neural Network Named-Entity Recognition
• Semi-Supervised Disentangled Framework for Transferable Named Entity Recognition
• A Survey on Recent Advances in Sequence Labeling from Deep Learning Models
• GRN: Gated Relation Network to Enhance Convolutional Neural Network for Named Entity Recognition
• MASK: A flexible framework to facilitate de-identification of clinical texts
• Named Entity Sequence Classification