no code implementations • Findings (NAACL) 2022 • Xin Sheng, Linli Xu, Yinlong Xu, Deqiang Jiang, Bo Ren
We propose a novel siamese generative adversarial net for abstractive text summarization (SSPGAN), which can preserve the main semantics of the source text.
no code implementations • COLING 2022 • Xin Sheng, Linli Xu, Yinlong Xu, Changcun Bao, Huang Chen, Bo Ren
The discriminator of CoCGAN discriminates the authenticity of given samples and optimizes a contrastive learning objective to capture both more flexible data-to-class relations and data-to-data relations among training samples.
no code implementations • 22 May 2022 • Jiquan Li, Junliang Guo, Yongxin Zhu, Xin Sheng, Deqiang Jiang, Bo Ren, Linli Xu
The task of Grammatical Error Correction (GEC) has received remarkable attention with wide applications in Natural Language Processing (NLP) in recent years.