Chengyue Gong

Switchable Decision: Dynamic Neural Generation Networks

2024 · arXiv (Cornell University)

Auto-regressive generation models achieve competitive performance across many different NLP tasks such as summarization, question answering, and classifications. However, they are also known for being slow in inference, which makes them challenging to deploy in …

Improving Neural Language Modeling via Adversarial Training

2019 · arXiv (Cornell University)

Recently, substantial progress has been made in language modeling by using deep neural networks. However, in practice, large scale neural language models have been shown to be prone to overfitting. In this paper, we present …