Empower Sequence Labeling with Task-Aware Neural Language Model

Abstract

Linguistic sequence labeling is a general modeling approach that encompasses a variety of problems, such as part-of-speech tagging and named entity recognition. Recent advances in neural networks (NNs) make it possible to build reliable models without handcrafted features. However, in many cases, it is hard to obtain sufficient annotations to train these models. In this study, we develop a novel neural framework to extract abundant knowledge hidden in raw texts to empower the sequence labeling task. Besides word-level knowledge contained in pre-trained word embeddings, character-aware neural language models are incorporated to extract character-level knowledge. Transfer learning techniques are further adopted to mediate different components and guide the language model towards the key knowledge. Comparing to previous methods, these task-specific knowledge allows us to adopt a more concise model and conduct more efficient training. Different from most transfer learning methods, the proposed framework does not rely on any additional supervision. It extracts knowledge from self-contained order information of training sequences. Extensive experiments on benchmark datasets demonstrate the effectiveness of leveraging character-level knowledge and the efficiency of co-training. For example, on the CoNLL03 NER task, model training completes in about 6 hours on a single GPU, reaching F1 score of 91.71$\pm$0.10 without using any extra annotation.

AAAI 2018

Cited by in corpus (13)

• TENER: Adapting Transformer Encoder for Named Entity Recognition
• Exploiting BERT for End-to-End Aspect-based Sentiment Analysis
• DOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction
• Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learning
• FLAT: Chinese NER Using Flat-Lattice Transformer
• GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling
• DomBERT: Domain-oriented Language Model for Aspect-based Sentiment Analysis
• Low Resource Multi-Task Sequence Tagging -- Revisiting Dynamic Conditional Random Fields
• Partially-Typed NER Datasets Integration: Connecting Practice to Theory
• Sentiment Tagging with Partial Labels using Modular Architectures
• Named Entity Recognition on Code-Switched Data: Overview of the CALCS 2018 Shared Task
• Learning A Unified Named Entity Tagger From Multiple Partially Annotated Corpora For Efficient Adaptation
• Eliciting Knowledge from Experts:Automatic Transcript Parsing for Cognitive Task Analysis