2 papers
cs.CL2019
Improving Cross-Domain Chinese Word Segmentation with Word Embeddings
Yuxiao Ye, Yue Zhang, Weikang Li +2
Cross-domain Chinese Word Segmentation (CWS) remains a challenge despite recent progress in neural-based CWS. The limited amount of annotated data in the target domain has been the…
cs.CL2018
Learning Universal Sentence Representations with Mean-Max Attention Autoencoder
Minghua Zhang, Yunfang Wu, Weikang Li +1
In order to learn universal sentence representations, previous methods focus on complex recurrent neural networks or supervised learning. In this paper, we propose a mean-max atten…