Dawei Zhu

Neural Data-to-Text Generation with LM-based Text Augmentation

2021 · arXiv (Cornell University)

For many new application domains for data-to-text generation, the main obstacle in training neural models consists of a lack of training data. While usually large numbers of instances are available on the data side, often …

Meta Self-Refinement for Robust Learning with Weak Supervision

2022 · arXiv (Cornell University)

Training deep neural networks (DNNs) under weak supervision has attracted increasing research attention as it can significantly reduce the annotation cost. However, labels from weak supervision can be noisy, and the high capacity of DNNs …

RepCL: Exploring Effective Representation for Continual Text Classification

2023 · arXiv (Cornell University)

Continual learning (CL) aims to constantly learn new knowledge over time while avoiding catastrophic forgetting on old tasks. In this work, we focus on continual text classification under the class-incremental setting. Recent CL studies find …