Using Error Decay Prediction to Overcome Practical Issues of Deep Active Learning for Named Entity Recognition
Paper • 1911.07335 • Published
Haw-Shiuan Chang
hschang
AI & ML interests
None yet
Recent Activity
authored a paper about 12 hours ago
Using Error Decay Prediction to Overcome Practical Issues of Deep Active
Learning for Named Entity Recognition authored a paper about 12 hours ago
PROMPT2BOX: Uncovering Entailment Structure among LLM Prompts authored a paper about 12 hours ago
Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic ApplicationsOrganizations
None yet
authored 19
papers about 12 hours ago
PROMPT2BOX: Uncovering Entailment Structure among LLM Prompts
Paper • 2603.21438 • Published
Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications
Paper • 2103.15330 • Published
Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling
Paper • 2210.05043 • Published
Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond
Paper • 2305.12289 • Published
Encoding Multi-Domain Scientific Papers by Ensembling Multiple CLS Tokens
Paper • 2309.04333 • Published
To Copy, or not to Copy; That is a Critical Issue of the Output Softmax Layer in Neural Sequential Recommenders
Paper • 2310.14079 • Published
Latent Traits and Cross-Task Transfer: Deconstructing Dataset Interactions in LLM Fine-tuning
Paper • 2509.13624 • Published
REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy
Paper • 2406.07735 • Published
CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints
Paper • 2410.04197 • Published
Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM
Paper • 2411.01610 • Published
CoKe: Customizable Fine-Grained Story Evaluation via Chain-of-Keyword Rationalization
Paper • 2503.17136 • Published
Multi-facet Universal Schema
Paper • 2103.15339 • Published
Changing the Mind of Transformers for Topically-Controllable Language Generation
Paper • 2103.15335 • Published
Efficient Graph-based Word Sense Induction by Distributional Inclusion Vector Embeddings
Paper • 1804.03257 • Published
Distributional Inclusion Vector Embedding for Unsupervised Hypernymy Detection
Paper • 1710.00880 • Published
Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples
Paper • 1704.07433 • Published
Automatically Extracting Action Graphs from Materials Science Synthesis Procedures
Paper • 1711.06872 • Published
Your Mouse and Eyes Secretly Leak Your Preference: LLM Alignment using Implicit Feedback from Users
Paper • 2606.20482 • Published