Search Results for author:
Found 10 papers, 1 papers with code
Entity Enhanced BERT Pre-training for Chinese NER
We then integrate the entity information into BERT using Char-Entity-Transformer, which augments the self-attention using a combination of character and entity representations.
Gender Bias in Large Language Models across Multiple Languages
We investigate the outputs of the GPT series of LLMs in various languages using our three measurement methods.
Generalizing Reward Modeling for Out-of-Distribution Preference Learning
During meta-training, a bilevel optimization algorithm is utilized to learn a reward model capable of guiding policy learning to align with human preferences across various distributions.
Discrepancy-Optimal Meta-Learning for Domain Generalization
This work attempts to tackle the problem of domain generalization (DG) via learning to reduce domain shift with an episodic training procedure.
Sparsely Overlapped Speech Training in the Time Domain: Joint Learning of Target Speech Separation and Personal VAD Benefits
This paper proposes the weighted SI-SNR loss, together with the joint learning of target speech separation and personal VAD.
Steady-state joint distribution for first-order stochastic reaction kinetics
Here we develop a novel method of computing the exact joint distributions of a wide class of first-order stochastic reaction systems in steady-state conditions.
Multi-Cell Compositional LSTM for NER Domain Adaptation
Cross-domain NER is a challenging yet practical problem.
Small protein number effects in stochastic models of autoregulated bursty gene expression
Furthermore we show that our model predictions for the protein number distribution are significantly different from those of Kumar et al. when the protein mean is small, gene switching is fast, and protein binding is faster than unbinding.
Exact power spectrum in a minimal hybrid model of stochastic gene expression oscillations
In our model, oscillations tend to occur when the protein is relatively stable and when gene switching is relatively slow.
Cross-Domain NER using Cross-Domain Language Modeling
Due to limitation of labeled resources, cross-domain named entity recognition (NER) has been a challenging task.
