A Double Adversarial Network Model for Multi-Domain and Multi-Task Chinese Named Entity Recognition

SUMMARY Named Entity Recognition (NER) systems are often realized by supervised methods such as CRF and neural network methods, which require large annotated data. In some domains that small annotated training data is available, multi-domain or multi-task learning methods are often used. In this paper, we explore the methods that use news domain and Chinese Word Segmentation (CWS) task to improve the performance of Chinese named entity recognition in weibo domain. We first propose two baseline models combining multi-domain and multi-task information. The two baseline models share information between di ff erent domains and tasks through sharing parameters simply. Then, we propose a Double AD-Versarial model (DoubADV model). The model uses two adversarial networks considering the shared and private features in di ff erent domains and tasks. Experimental results show that our DoubADV model outperforms other baseline models and achieves state-of-the-art performance compared with previous works in multi-domain and multi-task situation.

• Publication year

  2020

• Venue

  IEICE Trans. Inf. Syst.

• Publication date

  2020-07-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1587/transinf.2019edp7253
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• mechanism

  2020cited by this paper
• CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognition

  2019influential reference
• Glyce: Glyph-vectors for Chinese Character Representations

  2019influential reference
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

  2019cited by this paper
• Adversarial Transfer Learning for Chinese Named Entity Recognition with Self-Attention Mechanism

  2018influential reference
• Label-Aware Double Transfer Learning for Cross-Specialty Medical Named Entity Recognition

  2018cited by this paper
• Neural Adaptation Layers for Cross-domain Named Entity Recognition

  2018cited by this paper
• Multi-Task Learning for Sequence Tagging: An Empirical Study

  2018cited by this paper
• Adversarial Learning for Chinese NER from Crowd Annotations

  2018cited by this paper
• GENERATIVE ADVERSARIAL NETS

  2018cited by this paper
• Chinese NER Using Lattice LSTM

  2018influential reference
• Part-of-Speech Tagging for Twitter with Adversarial Neural Networks

  2017cited by this paper
• Aspect-augmented Adversarial Networks for Domain Adaptation

  2017cited by this paper
• Adversarial Multi-Criteria Learning for Chinese Word Segmentation

  2017cited by this paper
• Cross-Lingual Transfer Learning for POS Tagging without Cross-Lingual Resources

  2017cited by this paper
• A Unified Model for Cross-Domain and Semi-Supervised Named Entity Recognition in Chinese Social Media

  2017cited by this paper
• Domain Adaptation in Computer Vision Applications

  2017cited by this paper
• Adversarial Multi-task Learning for Text Classification

  2017cited by this paper
• F-Score Driven Max Margin Neural Network for Named Entity Recognition in Chinese Social Media

  2016influential reference
• Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks

  2016cited by this paper
• Improving Named Entity Recognition for Chinese Social Media with Word Segmentation Representation Learning

  2016influential reference
• Neural Architectures for Named Entity Recognition

  2016cited by this paper
• Multi-task Domain Adaptation for Sequence Tagging

  2016cited by this paper
• Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification

  2016cited by this paper
• Overview of the NLPCC-ICCPOL 2016 Shared Task: Chinese Word Segmentation for Micro-Blog Texts

  2016cited by this paper
• Character-Based LSTM-CRF with Radical-Level Features for Chinese Named Entity Recognition

  2016cited by this paper
• Domain-Adversarial Training of Neural Networks

  2015cited by this paper
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks

  2015cited by this paper
• Named Entity Recognition for Chinese Social Media with Jointly Trained Embeddings

  2015influential reference
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Information Extraction over Structured Data: Question Answering with Freebase

  2014cited by this paper
• Distributed Representations of Words and Phrases and their Compositionality

  2013cited by this paper
• Natural Language Processing (Almost) from Scratch

  2011cited by this paper
• Understanding the difficulty of training deep feedforward neural networks

  2010cited by this paper
• Chinese Word Segmentation and Named Entity Recognition Based on Conditional Random Fields

  2008cited by this paper
• The Third International Chinese Language Processing Bakeoff: Word Segmentation and Named Entity Recognition

  2006cited by this paper
• Chinese Named Entity Recognition with Conditional Random Fields

  2006cited by this paper
• Framewise phoneme classification with bidirectional LSTM networks

  2005cited by this paper
• The Second International Chinese Word Segmentation Bakeoff

  2005cited by this paper
• Framewise Phoneme Classification with Bidirectional Lstm Networks

  2005cited by this paper
• A Shortest Path Dependency Kernel for Relation Extraction

  2005cited by this paper
• Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

  2001cited by this paper
• Long Short-Term Memory

  1997cited by this paper

• No citing papers are available for this paper.