Multi-Criteria Learning for Chinese Word Segmentation

adversarial multi criteria learning for chinese n.w
1 / 24
Embed
Share

Explore the concept of Chinese word segmentation (CWS) through adversarial multi-criteria learning, focusing on advancements in natural language processing. Discover research on neural network-based CWS models and adversarial loss functions for improved segmentation accuracy.

  • Chinese Word Segmentation
  • NLP
  • Adversarial Learning
  • Neural Networks
  • Segmentation Models
rayaanacharya
freiburger_k Follow

Uploaded on | 0 Views

Download Presentation

Please find below an Image/Link to download the presentation.

The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.

You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.

Download Presentation

The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.

E N D

Presentation Transcript

  1. Adversarial Multi-Criteria Learning for Chinese Word Segmentation Xinchi Chen (Fudan University) Advisors: Prof. Xuanjing Huang Prof. Xipeng Qiu Direction: Natural Language Processing 1

  2. What is Chinese word segmentation (CWS) ? / / / / / / / / / / / / / / / / / / /

  3. 1 1. N. Xue. 2003. Chinese word segmentation as character tagging. Computational Linguistics and Chinese Language Processing 8(1):29 48.

  4. B E B E S S B E B E B E S / / / / / / /

  5. Long Short-term Neural Network based CWS [X Chen, X Qiu, C Zhu, P Liu, X Huang; EMNLP 2015] 5

  6. Adversarial Multi-Criteria Learning for Chinese Word Segmentation [X Chen, Zhan Shi, X Qiu, X Huang; ACL 2017] 6

  7. Adversarial Multi-Criteria Learning for Chinese Word Segmentation [X Chen, Zhan Shi, X Qiu, X Huang; ACL 2017] 7

  8. Adversarial Multi-Criteria Learning for Chinese Word Segmentation [X Chen, Zhan Shi, X Qiu, X Huang; ACL 2017] 8

  9. Objective function

  10. Unsupervised Domain Adaptation by Backpropagation [Yaroslav Ganin, et al.] 10

  11. Adversarial Multi-Criteria Learning for Chinese Word Segmentation [X Chen, Zhan Shi, X Qiu, X Huang; ACL 2017] 11

  12. Adversarial loss function The criterion discriminator maximizes the cross-entropy of predicted criterion distribution p( |X) and true criterion. An adversarial loss aims to produce shared features, such that a criterion discriminator cannot reliably predict the criterion by using these shared features. Therefore, we maximize the entropy of predicted criterion distribution when training shared parameters.

  13. Training 13

  14. Experiments 14

  15. Experiments 15

  16. Experiments 16

  17. Experiments 17

  18. Experiments 18

  19. Error Analysis 19

  20. Case Study 20

  21. Knowledge Transfer Simplified Chinese to Traditional Chinese Formal Texts to Informal Texts 21

  22. Simplified Chinese to Traditional Chinese 22

  23. Formal Texts to Informal Texts 23

  24. Thank you for your attention! Xinchi Chen (Fudan University) Advisors: Prof. Xuanjing Huang Prof. Xipeng Qiu Direction: Natural Language Processing 24

Related


Adversarial Machine Learning in Cybersecurity: Challenges and Defenses

Adversarial Machine Learning in Cybersecurity: Challenges and Defenses

thirza
Heightmap Segmentation in DICOM Imaging

Heightmap Segmentation in DICOM Imaging

frances
Adversarial Machine Learning in Cybersecurity

Adversarial Machine Learning in Cybersecurity

bartholomew
Mastering Market Segmentation: A Comprehensive Session Plan

Mastering Market Segmentation: A Comprehensive Session Plan

aurelio
Adversarial Attacks in Machine Learning

Adversarial Attacks in Machine Learning

yese_788
Adversarial Machine Learning Attacks

Adversarial Machine Learning Attacks

sand_379
Adversarial Threats in Machine Learning

Adversarial Threats in Machine Learning

pjab
Limitations of Deep Learning in Adversarial Settings

Limitations of Deep Learning in Adversarial Settings

fath_yde
Distillation as a Defense Against Adversarial Perturbations in Deep Neural Networks

Distillation as a Defense Against Adversarial Perturbations in Deep Neural Networks

pame_5
Robustness to Adversarial Examples in Machine Learning

Robustness to Adversarial Examples in Machine Learning

rhai
Segmentation in Operating Systems

Segmentation in Operating Systems

keon673
Chinese Watercolor Painting Style in Game Design

Chinese Watercolor Painting Style in Game Design

boha_huy
Understanding Zero-Shot Adversarial Robustness for Large-Scale Models

Understanding Zero-Shot Adversarial Robustness for Large-Scale Models

simmerman_b
The Cultural Significance of Chinese Names

The Cultural Significance of Chinese Names

cell
Perception and Segmentation in Autonomous Cyber-Physical Systems

Perception and Segmentation in Autonomous Cyber-Physical Systems

uroo
Chinese 1 Lesson Plan - Aug 25-29

Chinese 1 Lesson Plan - Aug 25-29

rigs342
Enhancing Student Engagement with the Local Chinese Community

Enhancing Student Engagement with the Local Chinese Community

kroh_di
Applied Learning Chinese for Non-Chinese Speaking Students (ApL(C))

Applied Learning Chinese for Non-Chinese Speaking Students (ApL(C))

kia_scr
Unlock the Power of Learning Chinese with Flashcards

Unlock the Power of Learning Chinese with Flashcards

fed_sch
Multi-class Skin Lesion Segmentation for Cutaneous T-cell Lymphomas

Multi-class Skin Lesion Segmentation for Cutaneous T-cell Lymphomas

kbono
Efficient Image Compression Model to Defend Adversarial Examples

Efficient Image Compression Model to Defend Adversarial Examples

roja_iz
Defense Against Adversarial Images using Web-Scale Nearest-Neighbor Search

Defense Against Adversarial Images using Web-Scale Nearest-Neighbor Search

maydelinh

More Related Content