Languages using Chinese characters are mostly processed at word level. Inspired by recent success of deep learning, we delve deeper to character and radical levels for Chinese language processing. We propose a new deep learning technique, called "radical embedding", with justifications based on Chinese linguistics, and validate its feasibility and utility through a set of three experiments: two in-house standard experiments on short-text categorization (STC) and Chinese word segmentation (CWS), and one in-field experiment on search ranking. We show that radical embedding achieves comparable, and sometimes even better, results than competing methods.
For nonsmall cell lung cancer (NSCLC) patients without distant metastases, occult involvement of N2 lymph nodes would be of the utmost importance in determining both treatment and survival. The key to optimal treatment strategies relied on accurate diagnosis, in particular accurate clinical tumor staging. Patients with clinical N0 or N1 staging preoperatively had a sizeable risk to have occult N2 lymph nodes metastases.From November 2004 to March 2007, the entire database in a tertiary hospital of all patients with a pathologic diagnosis of squamous NSCLC underwent anatomical pulmonary resection and systematic mediastinal lymph node dissection were retrospectively collected and reviewed. A nomogram was developed on the basis of a multivariable logistic regression model with a combination of all potential variables. In order to surmount the potential of overestimating predictive performance, both bootstrapping for internal validation and an independent external validation set were employed.A nomogram incorporating the significant risk factors was created to predict the probability of occult N2 lymph nodes metastases. The calibration plot for the probability of occult N2 lymph nodes metastases showed an optimal agreement between the predicted probabilities by nomogram and actual observed probabilities. An objective and accurate nomogram predictive model for occult N2 lymph nodes metastases was drawn up and validated internally and externally in patients with squamous NSCLC.The nomogram model, as a robust tool in predicting occult N2 lymph nodes involvement, could be involved in a cost-effective application of specific diagnostic and therapeutic strategies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.