There is growing interest in the tasks of financial text mining. Over the past few years, the progress of Natural Language Processing (NLP) based on deep learning advanced rapidly. Significant progress has been made with deep learning showing promising results on financial text mining models. However, as NLP models require large amounts of labeled training data, applying deep learning to financial text mining is often unsuccessful due to the lack of labeled training data in financial fields. To address this issue, we present FinBERT (BERT for Financial Text Mining) that is a domain specific language model pre-trained on large-scale financial corpora. In FinBERT, different from BERT, we construct six pre-training tasks covering more knowledge, simultaneously trained on general corpora and financial domain corpora, which can enable FinBERT model better to capture language knowledge and semantic information. The results show that our FinBERT outperforms all current state-of-the-art models. Extensive experimental results demonstrate the effectiveness and robustness of FinBERT. The source code and pre-trained models of FinBERT are available online.
Purpose: End-stage OA of the knee can cause a remarkable pain, and decrease the physical activity of the patients. Total knee arthroplasty (TKA) is an effective way to relieve pain and increase physical activity. Education is recommended for the management of osteoarthritis. But until now, we don't have any data about the effect of education for daily physical activity level recovery of osteoarthritis after total knee arthroplasty. The aim of this study is to provide an evidence of the effect of education for daily physical activity of osteoarthritis after total knee arthroplasty using accelerometry. Methods: We enrolled 50 female knee OA patients. The inclusion criteria were: age between 55 and 75; the diagnosis was knee osteoarthritis with the Kellgren/Lawrence grade 4; the body mass index (BMI) was less than 35; affected by the unilateral knee OA undergoing primary knee TKA; living in Beijing. The exclusion criteria were: infectious joint diseases; hip joint disease or ankle joint disease which affected the daily physical activities; co-morbidities such as chronic obstructive pulmonary disease which affected the daily physical activities. The 50 patients were randomly divided into education group and noneducation group. The education group was educated additionally by telephone every month after the TKA surgery. The non-education group was not educated additionally except for visit time. At last 25 patients were in education group, and 25 patients were in non-education group. We visit the 50 patients at the following time point: before surgery, 2 weeks after the surgery, 6weeks after the surgery, 3 months after the surgery, and 6 months after the surgery. We used the accelerometer (Fitbit Inc., US) to provide an objective measure of physical activity. At every visit time, the patient was recorded by the accelerometer for a whole week. During every visit time, we also performed the 30-s chair-stand test, 40 m fast-paced walk test, 12 stair-climb test, timed up-and-go test, 6-min walk test to evaluate the physical ability, used WOMAC score and KSS score to evaluate the function of the knee, used SF-12 to evaluate the life quality, used VAS score to evaluate the pain, and used CASI score to evaluate the satisfaction. We also collected the demographic data and the HSS Knee Surgery Expectation Survey data before surgery. At last, we compare the data of the two group. Results: There was a significant difference between the two groups 3 months and 6 months after surgery.(3 months, education group 5507.48±837.74, non-education group 4787.19±1038.15. 6 months, education group 6974.10±1396.10, non-education group 5471.70±1243.75). There was no significant difference between the two groups for other tests except for the 40-m fast paced walk test 3 months and 6 months after surgery. Conclusions: Education for the osteoarthritis patients after TKA surgery can help to improve the daily physical activity level after surgery, especially 3 months after the surgery. Education cannot help to improve most of the physical function...
Objective: To investigate the association between macrosomia and high weight-for-length/height in 1-3 years old Chinese infants. Design: A retrospective longitudinal study. Subjects: 918 children aged 1-3 years in Shanghai, China. Measurements: Body weight and length/height, illness status and feeding modalities were obtained during follow-up. Macrosomia was defined as birth weight X90th percentile of sex specific birth weight distribution. High weight-for-length/ height was defined as a weight-for-length/height z-score X1.68 using the WHO growth reference. Results: The odds ratios (ORs) for high weight-for-length/height were 3.60 (95% confidence interval (CI), 1.74-7.42) for boys and 1.39 (95% CI, 0.51-3.81) for girls who were macrosomic compared with the nonmacrosomic counterparts after adjustment for age. The ORs were attenuated to 3.48 (95% CI, 1.63-7.43) for boys and were still nonsignificant for girls (OR, 1.38; 95% CI, 0.49-3.91) after further controlling for illness status, the age of breast-feeding cessation and the age at introduction of complementary foods. From the analysis of boys and girls combined, the ORs were 2.48 (95% CI, 1.40-4.40) with adjustment for age and sex and 2.33 (95% CI, 1.29-4.22) with all covariates. Conclusion: Macrosomia is an important predictor for high weight-for-length/height in Chinese children aged 1-3 years.
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.