Chao Deng

Meta Auxiliary Learning for Low-resource Spoken Language Understanding

2022 · arXiv (Cornell University)

Spoken language understanding (SLU) treats automatic speech recognition (ASR) and natural language understanding (NLU) as a unified task and usually suffers from data scarcity. We exploit an ASR and NLU joint training method based on …

ESCL: Equivariant Self-Contrastive Learning for Sentence Representations

2023

Previous contrastive learning methods for sentence representations often focus on insensitive transformations to produce positive pairs, but neglect the role of sensitive transformations that are harmful to semantic representations. Therefore, we propose an Equivariant Self-Contrastive …

Short-term Prediction Method of Distributed Photovoltaic Power Generation Based on LSTM Network

2023

High-precision prediction of distributed photovoltaic power is crucial for the secure and stable operation of new power systems. The conventional prediction models based on forward neural networks or regression analyses lack historical memory, which result …