Abstract Background To provide satisfying answers, medical QA system has to understand the intentions of the users’ questions precisely. For medical intent classification, it requires high-quality datasets to train a deep-learning approach in a supervised way. Currently, there is no public dataset for Chinese medical intent classification, and the datasets of other fields are not applicable to the medical QA system. To solve this problem, we construct a Chinese medical intent dataset (CMID) using the questions from medical QA websites. On this basis, we compare four intent classification models on CMID using a case study. Methods The questions in CMID are obtained from several medical QA websites. The intent annotation standard is developed by the medical experts, which includes four types and 36 subtypes of users’ intents. Besides the intent label, CMID also provides two types of additional information, including word segmentation and named entity. We use the crowdsourcing way to annotate the intent information for each Chinese medical question. Word segmentation and named entities are obtained using the Jieba and a well-trained Lattice-LSTM model. We loaded a Chinese medical dictionary consisting of 530,000 for word segmentation to obtain a more accurate result. We also select four popular deep learning-based models and compare their performances of intent classification on CMID. Results The final CMID contains 12,000 Chinese medical questions and is organized in JSON format. Each question is labeled the intention, word segmentation, and named entity information. The information about question length, number of entities, and are also detailed analyzed. Among Fast Text, TextCNN, TextRNN, and TextGCN, Fast Text and TextCNN models have achieved the best results in four types and 36 subtypes intent classification, respectively. Conclusions In this work, we provide a dataset for Chinese medical intent classification, which can be used in medical QA and related fields. We performed an intent classification task on the CMID. In addition, we also did some analysis on the content of the dataset.
Digital empowerment of China’s power energy sector is a key factor in increasing its economic and social benefits, and named entity recognition technology is the most fundamental and core task of information extraction technology in the digital empowerment process. Therefore, we propose a multimodal named entity recognition model PE-MNER for power equipment based on deep neural networks. Compared to text multimodality, text and image multimodality can use image information to supplement missing information in the text, thus enabling more accurate entity extraction. The model first obtains a BERT neural network through incremental training, and then extracts Chinese character features through the network. Then, a hierarchical visual prefix fusion network is used to fuse image information. From the comparative experimental results, it can be seen that the proposed model has the best performance compared to the benchmark model, with an improvement of 4.08%∼7.20% in the F1 score compared to the benchmark model.
Targeted therapy has become a powerful approach for cancer treatment. Better understanding of oncogenes as well as synthetic lethal interactions with oncogenes will lead to new strategies for tumor-specific treatment. It is well known that mutant p53 plays an important role in tumorigenesis and tumor development. Thus, understanding the synthetic lethal relationship between p53 mutations and interacting genes in tumor is critical for the personalized treatments of p53 mutant tumors. Synthetic lethal genes to mutant p53 can be divided into cell cycle regulators and non-cell cycle regulators. This paper review show these two types of target genes contribute to synthetic lethal interactions with p53 mutations and potential applications of these interactions in anticancer therapy. 恶性肿瘤的靶向治疗已经成为现阶段肿瘤治疗的热点。随着人们对癌基因认知的加深,借助合成致死的方法靶向治疗肿瘤已成为针对肿瘤特异性治疗的新策略。p53基因突变在肿瘤的形成和发展过程中具有重要作用。因此,了解肿瘤中与突变型p53基因有合成致死关系的靶基因的作用方式,有助于指导由突变型p53基因诱发肿瘤的个性化治疗。与突变型p53基因具有合成致死关系的靶基因可分为细胞周期调控基因和细胞非周期调控基因,文章综述了这两类靶基因与突变型p53基因如何构成合成致死作用以及此作用的现实意义。.
The hybrid screen leverages two halftoning techniques, screening and direct binary search (DBS), to achieve the better quality of the halftoned images, and to enable the algorithm to be integrated into low-cost printers with limited computational resources. This work proposes a complete hybrid screen design method for multilevel output with unequal resolution printing pixels in a laser electrophotographic system. Because of the unstable rendering output of the electrophotographic process, we adopt a clustered- dot screen in our work. We also use the supercell approach to solve the trade-off between screen frequency and the effective number of quantization levels that is inherent to a cluster-dot screen. Moreover, we use subpixel modeling to simulate the unequal resolution printing pixels and multilevel output. This method is well-suited to development of halftoning algorithms for systems with unequal resolution. We also explore several design rules to evaluate the impact on printing quality.
In order to improve the accuracy of information extraction in multimodal electric power operation and inspection data and to solve the problem of aligning electric power text records with image records, a knowledge extraction method for electric power equipment operation and inspection oriented to multimodal data is proposed. First, the constructed alignment network uses the contrast loss to find the operation and inspection images from multiple images that are consistent with the description of the text records; then, the parameters in the alignment network are frozen, and a two-pointer network is constructed to extract the subject names of the electric equipment or components in the electric operation and inspection records, and the designed multimodal fusion module and the subject information are utilized to predict the location of the guest under different electric operation and inspection relationships, and to complete the electric operation and inspection ternary group Prediction. The method is validated on the power equipment operation and inspection dataset and the public dataset, and the experimental results show that the method has a better effect on graphical.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)