Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks

Abstract

Recent papers have shown that neural networks obtain state-of-the-art performance on several different sequence tagging tasks. One appealing property of such systems is their generality, as excellent performance can be achieved with a unified architecture and without task-specific feature engineering. However, it is unclear if such systems can be used for tasks without large amounts of training data. In this paper we explore the problem of transfer learning for neural sequence taggers, where a source task with plentiful annotations (e.g., POS tagging on Penn Treebank) is used to improve performance on a target task with fewer available annotations (e.g., POS tagging for microblogs). We examine the effects of transfer learning for deep hierarchical recurrent networks across domains, applications, and languages, and show that significant improvement can often be obtained. These improvements lead to improvements over the current state-of-the-art on several well-studied tasks.

Accepted as a conference paper at ICLR 2017. This is an extended version of the original paper (https://arxiv.org/abs/1603.06270). The original paper proposes a new architecture, while this version focuses on transfer learning for a general model class

Cited by in corpus (6)

• Neural Aspect and Opinion Term Extraction with Mined Rules as Weak Supervision
• GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling
• Extracting Symptoms and their Status from Clinical Conversations
• Modelling Domain Relationships for Transfer Learning on Retrieval-based Question Answering Systems in E-commerce
• Multi-Task Learning with Contextualized Word Representations for Extented Named Entity Recognition
• Variational Sequential Labelers for Semi-Supervised Learning