Skip to main navigation
Skip to search
Skip to main content
Illinois Experts Home
LOGIN & Help
Home
Profiles
Research units
Research & Scholarship
Datasets
Honors
Press/Media
Activities
Search by expertise, name or affiliation
CROSS-LINGUAL TRANSFER WITH CLASS-WEIGHTED LANGUAGE-INVARIANT REPRESENTATIONS
Ruicheng Xian,
Heng Ji
,
Han Zhao
Siebel School of Computing and Data Science
Coordinated Science Lab
National Center for Supercomputing Applications (NCSA)
Electrical and Computer Engineering
Research output
:
Contribution to conference
›
Paper
›
peer-review
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'CROSS-LINGUAL TRANSFER WITH CLASS-WEIGHTED LANGUAGE-INVARIANT REPRESENTATIONS'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Cross-lingual Transfer
100%
Language Task
100%
Target Language
100%
Invariant Representation
100%
Shared Representations
100%
Recent Advances
50%
Domain Alignment
50%
Performance Gain
50%
Invariance
50%
Shift Estimation
50%
Transfer Performance
50%
Non-parallel
50%
Across Languages
50%
Neural Modeling
50%
Semi-supervised Method
50%
Unsupervised Method
50%
Cross-lingual
50%
Feature Representation
50%
Distributional Shift
50%
Source Language
50%
Multilingual Models
50%
Negative Transfer
50%
Zero-shot
50%
Class Prior
50%
Parallel Texts
50%
Shift Correction
50%
Representation Alignment
50%
Computer Science
Invariant Representation
100%
Target Language
100%
Performance Gain
50%
Learning Technique
50%
Semisupervised Learning
50%
Affect Performance
50%
Language Modeling
50%
Source Language
50%
Social Sciences
Learning Method
100%
Multilingualism
100%
Language Modeling
100%