Search Results for author:
Found 8 papers, 2 papers with code
Learn to Adapt for Generalized Zero-Shot Text Classification
Generalized zero-shot text classification aims to classify textual instances from both previously seen classes and incrementally emerging unseen classes.
Generative Adversarial Networks with Decoder-Encoder Output Noise
The deep convolutional generative adversarial networks (DCGANs) were then proposed to leverage the quality of generated images.
Student's t-Generative Adversarial Networks
We propose a new method referring to conditional GAN, which equipments the latent noise with mixture of Student's t-distribution with attention mechanism in addition to class information.
Ensemble Making Few-Shot Learning Stronger
It is difficult for a single model to adapt to various relation learning, which results in the high variance problem.
P-INT: A Path-based Interaction Model for Few-shot Knowledge Graph Completion
Its general process is to first encode the implicit relation of an entity pair and then match the relation of a query entity pair with the relations of the reference entity pairs.
Causal Interventions-based Few-Shot Named Entity Recognition
Few-shot named entity recognition (NER) systems aims at recognizing new classes of entities based on a few labeled samples.
Intuitive or Dependent? Investigating LLMs' Behavior Style to Conflicting Prompts
Drawing on cognitive theory, we target the first scenario of decision-making styles where there is no superiority in the conflict and categorize LLMs' preference into dependent, intuitive, and rational/irrational styles.
