Yueting Zhuang

Ad Recommendation for Sponsored Search Engine via Composite Long-Short Term Memory

2016

Search engine logs contain a large amount of users' click-through data that can be leveraged as implicit indicators of relevance. In this paper we address ad recommendation problem that finding and ranking the most relevant …

Self-Supervised Class Incremental Learning

2021 · arXiv (Cornell University)

Existing Class Incremental Learning (CIL) methods are based on a supervised classification framework sensitive to data labels. When updating them based on the new class data, they suffer from catastrophic forgetting: the model cannot discern …

DiffusionNER: Boundary Diffusion for Named Entity Recognition

2023 · arXiv (Cornell University)

In this paper, we propose DiffusionNER, which formulates the named entity recognition task as a boundary-denoising diffusion process and thus generates named entities from noisy spans. During training, DiffusionNER gradually adds noises to the golden …