Ta-Chung Chi
12 papers · 2017–2024 · 7 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (38) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π§¬
Topic Evolution
π
Keyword Champion
(3)
ποΈ
Keyword Collector
(64)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
π
Renaissance Researcher
(5)
Top co-authors
Research topics
Machine Learning
(11)
Deep Learning
(8)
Natural Language Processing
(8)
Generation
(6)
Artificial Intelligence
(5)
Core AI
(5)
Learning Types Β· Machine Learning
(5)
Learning Types Β· Deep Learning
(5)
Architectures
(4)
Core Methods
(4)
Optimization & Theory
(4)
Techniques
(2)
Interdisciplinary
(1)
Reinforcement Learning
(1)
Robotics
(1)
Keywords
length extrapolation
(5)
positional embedding
(3)
attention mechanism
(3)
transformer architecture
(3)
language model
(3)
zero-shot learning
(2)
regular language
(2)
prompt engineering
(1)
continual learning
(1)
representation learning
(1)
self-supervised learning
(1)
word sense disambiguation
(1)
text classification
(1)
cross-lingual embedding
(1)
reinforcement learning
(1)
language understanding
(1)
human-robot interaction
(1)
interactive learning
(1)
variance reduction
(1)
working memory
(1)
Papers
Advancing Regular Language Reasoning in Linear Recurrent Neural Networks
NAACL 2024
Attention Alignment and Flexible Positional Embeddings Improve Transformer Length Extrapolation
NAACL 2024
Dissecting Transformer Length Extrapolation via the Lens of Receptive Field Analysis
ACL 2023
Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings
ACL 2023
PESCO: Prompt-enhanced Self Contrastive Learning for Zero-shot Text Classification
ACL 2023
Transformer Working Memory Enables Regular Language Reasoning And Natural Language Length Extrapolation
EMNLP 2023
KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation
NeurIPS 2022
Training Discrete Deep Generative Models via Gapped Straight-Through Estimator
ICML 2022
Zero-Shot Dialogue Disentanglement by Self-Supervised Entangled Response Selection
EMNLP 2021
Just Ask: An Interactive Learning Framework for Vision and Language Navigation
AAAI 2020
CLUSE: Cross-Lingual Unsupervised Sense Embeddings
EMNLP 2018
Speaker Role Contextual Modeling for Language Understanding and Dialogue Policy Learning
IJCNLP 2017