MSRA
Related Papers
A Joint Model for Unsupervised Chinese Word Segmentation
In this paper, we propose a joint model for unsupervised Chinese word segmentation (CWS). Inspired by the “products of ex- perts” idea, our joint model firstly com- bines two generative …...
Long Short-Term Memory Neural Networks for Chinese Word Segmentation
Currently most of state-of-the-art meth- ods for Chinese word segmentation are based on supervised learning, whose fea- tures are mostly extracted from a local con- text. These methods cannot utilize …...
CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognition
AbstractNamed entity recognition (NER) in Chinese is essential but difficult because of the lack of natural delimiters. Therefore, Chinese Word Segmentation (CWS) is usually considered as the first step for …...
Dice Loss for Data-imbalanced NLP Tasks
AbstractMany NLP tasks such as tagging and machine reading comprehension are faced with the severe data imbalance issue: negative examples significantly outnumber positive examples, and the huge number of easy-negative …...