Ernie Chang
30 papers · 2017–2026 · 9 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
🏃 Academic Marathon (8) 🌍 Conference Polyglot (9) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (5)
🌈
Renaissance Researcher
(6)
🌍
Conference Polyglot
(9)
🏃
Academic Marathon
(8)
🤝
Dynamic Duo
(14)
👥
Mega-Team
(45)
🏆
Keyword Champion
(2)
💎
Century Club
(29)
⚡
Prolific Year
(5)
❓
The Questioner
🗃️
Keyword Collector
(131)
🔥
Unstoppable
(7)
Conferences
ACL (8)
COLING (5)
EMNLP (4)
EACL (3)
NAACL (3)
ICML (2)
IJCNLP (2)
INTERSPEECH (2)
SEMEVAL (1)
Top co-authors
Keywords
machine translation
(5)
text generation
(5)
few-shot learning
(4)
data-to-text generation
(4)
language model
(4)
low-resource language
(3)
natural language understanding
(3)
data annotation
(3)
multilingual model
(3)
knowledge distillation
(2)
multi-label prediction
(2)
instance selection
(2)
language model fine-tuning
(2)
zero-shot learning
(2)
text classification
(2)
ancient chinese
(2)
natural language generation
(2)
domain adaptation
(2)
transfer learning
(2)
active learning
(2)
Papers
IMPACT: Importance-Aware Activation Space Reconstruction
ACL 2026
Agent-as-a-Judge: Evaluate Agents with Agents
ICML 2025
AutoMixer: Checkpoint Artifacts as Automatic Data Mixers
ACL 2025
Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions
NAACL 2025
Self-Vocabularizing Training for Neural Machine Translation
NAACL 2025
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
ACL 2024
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
ICML 2024
Scaling Parameter-Constrained Language Models with Quality Data
EMNLP 2024
Target-Aware Language Modeling via Granular Data Sampling
EMNLP 2024
Navigating the Minefield of MT Beam Search in Cascaded Streaming Speech Translation
INTERSPEECH 2024
Towards Zero-Shot Multilingual Transfer for Code-Switched Responses
ACL 2023
Low-Resource Cross-Lingual Adaptive Training for Nigerian Pidgin
INTERSPEECH 2023
Revisiting Sample Size Determination in Natural Language Understanding
ACL 2023
A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translation
NAACL 2022
Programmable Annotation with Diversed Heuristics and Data Denoising
COLING 2022
Few-Shot Pidgin Text Adaptation via Contrastive Fine-Tuning
COLING 2022
Improving Zero-Shot Multilingual Text Generation via Iterative Distillation
COLING 2022
Two-Stage Movie Script Summarization: An Efficient Method For Low-Resource Long Document Summarization
COLING 2022
Time-Aware Ancient Chinese Text Translation and Inference
ACL 2021
Jointly Improving Language Understanding and Generation with Quality-Weighted Weak Supervision of Automatic Labeling
EACL 2021
Neural Data-to-Text Generation with LM-based Text Augmentation
EACL 2021
On Training Instance Selection for Few-Shot Neural Text Generation
IJCNLP 2021
Time-Aware Ancient Chinese Text Translation and Inference
IJCNLP 2021
Does the Order of Training Samples Matter? Improving Neural Data-to-Text Generation with Curriculum Learning
EACL 2021
On Training Instance Selection for Few-Shot Neural Text Generation
ACL 2021
Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence
ACL 2020
DART: A Lightweight Quality-Suggestive Data-to-Text Annotation Tool
COLING 2020
MovieChats: Chat like Humans in a Closed Domain
EMNLP 2020
Improving Language Generation from Feature-Rich Tree-Structured Data with Relational Graph Convolutional Encoders
EMNLP 2019
Neobility at SemEval-2017 Task 1: An Attention-based Sentence Similarity Model
SEMEVAL 2017