Adversarial Multi-Criteria Learning for Chinese Word Segmentation

Different linguistic perspectives causes many diverse segmentation criteria for Chinese word segmentation (CWS). Most existing methods focus on improve the performance for each single criterion. However, it is interesting to exploit these different criteria and mining their common underlying knowledge. In this paper, we propose adversarial multi-criteria learning for CWS by integrating shared knowledge from multiple heterogeneous segmentation criteria. Experiments on eight corpora with heterogeneous segmentation criteria show that the performance of each corpus obtains a significant improvement, compared to single-criterion learning. Source codes of this paper are available on Github.

• Publication year

  2017

• Venue

  Annual Meeting of the Association for Computational Linguistics

• Publication date

  2017-04-01

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.18653/v1/P17-1110arXiv 1704.07556
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• GENERATIVE ADVERSARIAL NETS

  2018cited by this paper
• Deep Multi-Task Learning with Shared Memory

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

  2016cited by this paper
• Neural Network for Heterogeneous Annotations

  2016cited by this paper
• Domain Separation Networks

  2016influential reference
• Recurrent Neural Network for Text Classification with Multi-Task Learning

  2016cited by this paper
• Fast Coupled Sequence Labeling on Heterogeneous Annotations via Context-aware Pruning

  2016cited by this paper
• Exploiting Heterogeneous Annotations for Weibo Word Segmentation and POS Tagging

  2015cited by this paper
• Domain-Adversarial Training of Neural Networks

  2015influential reference
• Long Short-Term Memory Neural Networks for Chinese Word Segmentation

  2015influential reference
• Gated Recursive Neural Network for Chinese Word Segmentation

  2015cited by this paper
• Multi-task Sequence to Sequence Learning

  2015cited by this paper
• Coupled Sequence Labeling on Heterogeneous Annotations: POS Tagging as a Case Study

  2015cited by this paper
• An Empirical Exploration of Recurrent Network Architectures

  2015cited by this paper
• Max-Margin Tensor Neural Network for Chinese Word Segmentation

  2014cited by this paper
• Domain-Adversarial Neural Networks

  2014cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Joint Chinese Word Segmentation and POS Tagging on Heterogeneous Annotated Corpora with Multiple Task Learning

  2013cited by this paper
• Deep Learning for Chinese Word Segmentation and POS Tagging

  2013cited by this paper
• Generating Sequences With Recurrent Neural Networks

  2013cited by this paper
• Efficient Estimation of Word Representations in Vector Space

  2013cited by this paper
• Reducing Approximation and Estimation Errors for Chinese Lexical Processing with Heterogeneous Annotations

  2012cited by this paper
• Automatic Adaptation of Annotation Standards: Chinese Word Segmentation and POS Tagging – A Case Study

  2009cited by this paper
• A unified architecture for natural language processing: deep neural networks with multitask learning

  2008cited by this paper
• The Fourth International Chinese Language Processing Bakeoff: Chinese Word Segmentation, Named Entity Recognition and Chinese POS Tagging

  2008cited by this paper
• The Second International Chinese Word Segmentation Bakeoff

  2005cited by this paper
• Exploiting Task Relatedness for Mulitple Task Learning

  2003cited by this paper
• Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

  2001cited by this paper
• The Part-Of-Speech Tagging Guidelines for the Penn Chinese Treebank (3.0)

  2000cited by this paper
• Multitask Learning

  1997cited by this paper

• Construction of a Geological Fault Corpus and Named Entity Recognition

  2025cites this paper
• A Probabilistic Toolkit for Multi-grained Word Segmentation in Chinese

  2025cites this paper
• Improving Chinese word segmentation with character–lexicon class attention

  2024cites this paper
• Self-training improves few-shot learning in legal artificial intelligence tasks

  2024cites this paper
• Word Boundary Decision: An Efficient Approach for Low-Resource Word Segmentation

  2024cites this paper
• The influence of iconography and tempera painting techniques on the Chinese school of art

  2023cites this paper
• Adversarial Multi-Task Learning for Mandarin Prosodic Boundary Prediction With Multi-Modal Embeddings

  2023cites this paper
• Advancing Multi-Criteria Chinese Word Segmentation Through Criterion Classification and Denoising

  2023influential citation
• Text Classification of Mixed Model Based on Deep Learning

  2023cites this paper
• The Uncertainty-based Retrieval Framework for Ancient Chinese CWS and POS

  2023cites this paper
• A Web Semantic-Based Text Analysis Approach for Enhancing Named Entity Recognition Using PU-Learning and Negative Sampling

  2023cites this paper
• Improving Multi-Criteria Chinese Word Segmentation through Learning Sentence Representation

  2023cites this paper
• Fine-Grained Domain Adaptation for Chinese Syntactic Processing

  2023cites this paper
• ODU Digital Commons ODU Digital Commons

  2022cites this paper
• GeoBERTSegmenter: Word Segmentation of Chinese Texts in the Geoscience Domain Using the Improved BERT Model

  2022cites this paper
• Enhancing Relation Extraction via Adversarial Multi-task Learning

  2022cites this paper
• Chinese Word Segmentation based on Word boundary Classificatioin

  2022cites this paper
• Security Hardening of Intelligent Reflecting Surfaces Against Adversarial Machine Learning Attacks

  2022cites this paper
• Point‐of‐interest detection from Weibo data for map updating

  2022cites this paper
• KGNER: Improving Chinese Named Entity Recognition by BERT Infused with the Knowledge Graph

  2022cites this paper
• Weighted self Distillation for Chinese word segmentation

  2022cites this paper
• Word Segmentation by Separation Inference for East Asian Languages

  2022cites this paper
• That Slepen Al the Nyght with Open Ye! Cross-era Sequence Segmentation with Switch-memory

  2022cites this paper
• Lexicon enhanced Chinese named entity recognition with pointer network

  2022cites this paper
• Research on Word Vector Training Method Based on Improved Skip‐Gram Algorithm

  2022cites this paper
• A study for extracting keywords from data with deep learning and suffix array

  2022cites this paper
• Chinese Word Segmentation with Heterogeneous Graph Neural Network

  2022cites this paper
• Advance research in agricultural text-to-speech: the word segmentation of analytic language and the deep learning-based end-to-end system

  2021cites this paper
• SAME: Scenario Adaptive Mixture-of-Experts for Promotion-Aware Click-Through Rate Prediction

  2021cites this paper
• Incorporating lexicon knowledge into Chinese NER using hierarchical meta-embedding

  2021cites this paper
• Lexicon-Based Graph Convolutional Network for Chinese Word Segmentation

  2021cites this paper
• Segment, Mask, and Predict: Augmenting Chinese Word Segmentation with Self-Supervision

  2021cites this paper
• Wasserstein Selective Transfer Learning for Cross-domain Text Mining

  2021cites this paper
• Domain-Aware Word Segmentation for Chinese Language: A Document-Level Context-Aware Model

  2021influential citation
• Enhancing Chinese Character Representation With Lattice-Aligned Attention

  2021cites this paper
• Span Labeling Approach for Vietnamese and Chinese Word Segmentation

  2021cites this paper
• 融合自编码器和对抗训练的中文新词发现方法(Finding Chinese New Word By Combining Self-encoder and Adversarial Training)

  2021cites this paper
• Multi-Lingual Question Generation with Language Agnostic Language Model

  2021cites this paper
• Handling Cross- and Out-of-Domain Samples in Thai Word Segmentation

  2021cites this paper
• Federated Chinese Word Segmentation with Global Character Associations

  2021cites this paper
• Modeling Multiple Coexisting Category-Level Intentions for Next Item Recommendation

  2021cites this paper
• Neural Joint Model for Part-of-Speech Tagging and Entity Extraction

  2021cites this paper
• Political Depolarization of News Articles Using Attribute-aware Word Embeddings

  2021cites this paper
• Pre-training with Meta Learning for Chinese Word Segmentation

  2021cites this paper
• An exploration of semi-supervised and language-adversarial transfer learning using hybrid acoustic model for hindi speech recognition

  2021cites this paper
• Bidirectional LSTM-CRF Attention-based Model for Chinese Word Segmentation

  2021cites this paper
• Named entity recognition of local adverse drug reactions in Xinjiang based on transfer learning

  2021cites this paper
• Chinese Named Entity Recognition: Applications and Challenges

  2021cites this paper
• Unsupervised Word Segmentation with Bi-directional Neural Language Model

  2021cites this paper
• A transfer learning model with multi-source domains for biomedical event trigger extraction

  2021cites this paper
• Domain Adaptation of Thai Word Segmentation Models Using Stacked Ensemble

  2020cites this paper
• Aspect level sentiment classification with unbiased attention and target enhanced representations

  2020cites this paper
• Exploring Segment Representations for Neural Semi-Markov Conditional Random Fields

  2020cites this paper
• Integrating Boundary Assembling into a DNN Framework for Named Entity Recognition in Chinese Social Media Text

  2020cites this paper
• Adversarial Transfer Learning for Punctuation Restoration

  2020cites this paper
• Unified Multi-Criteria Chinese Word Segmentation with BERT

  2020influential citation
• Multi-Level Representation Learning for Chinese Medical Entity Recognition: Model Development and Validation

  2020cites this paper
• Lattice LSTM for Chinese Sentence Representation

  2020cites this paper
• Learning not to Discriminate: Task Agnostic Learning for Improving Monolingual and Code-switched Speech Recognition

  2020cites this paper
• Improving Chinese Word Segmentation with Wordhood Memory Networks

  2020influential citation
• Coupling Distant Annotation and Adversarial Training for Cross-Domain Chinese Word Segmentation

  2020cites this paper
• Adversarial Learning for Multi-Task Sequence Labeling With Attention Mechanism

  2020influential citation
• Unseen Target Stance Detection with Adversarial Domain Generalization

  2020cites this paper
• fastHan: A BERT-based Joint Many-Task Toolkit for Chinese NLP

  2020cites this paper
• A multi-granularity knowledge association model of geological text based on hypernetwork

  2020cites this paper
• Domain Adaptation of Transformers for English Word Segmentation

  2020cites this paper
• Multitask deep learning for native language identification

  2020cites this paper
• Pre-trained Model for Chinese Word Segmentation with Meta Learning

  2020cites this paper
• A Double Adversarial Network Model for Multi-Domain and Multi-Task Chinese Named Entity Recognition

  2020cites this paper
• Chinese Word Segmentation via BiLSTM+Semi-CRF with Relay Node

  2020cites this paper
• Is Chinese Word Segmentation a Solved Task? Rethinking Neural Chinese Word Segmentation

  2020influential citation
• A Joint Multiple Criteria Model in Transfer Learning for Cross-domain Chinese Word Segmentation

  2020cites this paper
• Multi-grained Chinese Word Segmentation with Weakly Labeled Data

  2020cites this paper
• Research on Named Entity Recognition for Science and Technology Terms in Chinese Based on Dependent Entity Word Vector

  2020cites this paper
• UnihanLM: Coarse-to-Fine Chinese-Japanese Language Model Pretraining with the Unihan Database

  2020influential citation
• 半监督跨领域语义依存分析技术研究(Semi-supervised Domain Adaptation for Semantic Dependency Parsing)

  2020cites this paper
• An Improved Chinese Named Entity Recognition Method with TB-LSTM-CRF

  2020cites this paper
• Chinese Word Segmentation Based on Bi-GRU Integrating Dictionary Information

  2020cites this paper
• Research on Chinese New Word Recognition Method

  2020cites this paper
• Iterated dilated convolutional neural networks for word segmentation

  2020influential citation
• CMRS: Towards Intelligent Recommendation for Choosing College Majors

  2020cites this paper
• fastHan: A BERT-based Multi-Task Toolkit for Chinese NLP

  2020cites this paper
• A multi-Cross Matching Network for Chinese Named Entity Linking in Short Text

  2019cites this paper
• Unsupervised Learning Helps Supervised Neural Word Segmentation

  2019cites this paper
• Improving Cross-Domain Chinese Word Segmentation with Word Embeddings

  2019influential citation
• Language-Adversarial Transfer Learning for Low-Resource Speech Recognition

  2019cites this paper
• Cross-View Adaptation Network for Cross-Domain Relation Extraction

  2019cites this paper
• Glyce: Glyph-vectors for Chinese Character Representations

  2019cites this paper
• Improving Chinese Named Entity Recognition with Semantic Information of Character Multi-position Representation

  2019cites this paper
• A Concise Model for Multi-Criteria Chinese Word Segmentation with Transformer Encoder

  2019influential citation
• Robust Chinese Word Segmentation with Contextualized Word Representations

  2019cites this paper
• Adversarial Domain Adaptation for Chinese Semantic Dependency Graph Parsing

  2019cites this paper
• Vocabulary Pyramid Network: Multi-Pass Encoding and Decoding with Multi-Level Vocabularies for Response Generation

  2019cites this paper
• Word Segmentation for Chinese Judicial Documents

  2019cites this paper
• Leverage Lexical Knowledge for Chinese Named Entity Recognition via Collaborative Graph Network

  2019cites this paper
• Entity relationship extraction optimization based on entity recognition

  2019cites this paper
• Fine-grained Knowledge Fusion for Sequence Labeling Domain Adaptation

  2019influential citation
• BiLSTM-CRF for geological named entity recognition from the geoscience literature

  2019cites this paper
• Exploring Discriminative Word-Level Domain Contexts for Multi-Domain Neural Machine Translation

  2019cites this paper
• Fine-grained Chinese Named Entity Recognition in Entertainment News Using Adversarial Multi-task Learning

  2019cites this paper