Search

The automatic extraction of key entities in mechanics problems is an important means to automatically solve mechanics problems. Nevertheless, for standard Chinese, compared with the open domain, mechanics problems have a large number of specialized terms and composite entities, which leads to a low recognition capability. Although recent research demonstrates that external information and pre-trained language models can improve the performance of Chinese Named Entity Recognition (CNER), few efforts have been made to combine the two to explore high-performance algorithms for extracting mechanics entities. Therefore, this article proposes a Multi-Meta Information Embedding Enhanced Bidirectional Encoder Representation from Transformers (MMIEE-BERT) for recognizing entities in mechanics problems. The proposed method integrates lexical information and radical information into BERT layers directly by employing an information adapter layer (IAL). Firstly, according to the characteristics of Chinese, a Multi-Meta Information Embedding (MMIE) including character embedding, lexical embedding, and radical embedding is proposed to enhance Chinese sentence representation. Secondly, an information adapter layer (IAL) is proposed to fuse the above three embeddings into the lower layers of the BERT. Thirdly, a Bidirectional Long Short-Term Memory (BiLSTM) network and a Conditional Random Field (CRF) model are applied to semantically encode the output of MMIEE-BERT and obtain each character’s label. Finally, extensive experiments were carried out on the dataset built by our team and widely used datasets. The results demonstrate that the proposed method has more advantages than the existing models in the entity recognition of mechanics problems, and the precision, recall, and F1 score were improved. The proposed method is expected to provide an automatic means for extracting key information from mechanics problems.

Abstract Background Esophagogastroduodenoscopy is very useful in diagnosing and treating upper gastrointestinal mucosal disorders, but too much foam and water in stomach decrease its diagnostic efficiency. Simethicone administration can help remove excessive foam. Aims To determine the optimal simethicone administration strategies in a comparative randomized controlled clinical trial. Methods Adult outpatients with indications for esophagogastroduodenoscopy were enrolled and randomly divided into group 1 (simethicone solution intake 20–30 min before procedure, n = 110), group 2 (simethicone solution intake 31–60 min before procedure, n = 92), and group 3 (simethicone solution intake > 60 min before procedure). Primary and secondary outcomes were procedure time and the patients’ satisfaction after the examination. All symptoms like abdominal pain and distension were recorded. Results No statistically significant differences were found on the patients’ demographic and clinical features and mean examination time (all P values > 0.05). The distribution of patients with different endoscopic and pathological diagnosis was comparable among three groups, respectively (P = 0.607; P = 0.289). However, the proportion of patients with Gastric Cleanness Grade A was most in group 2 (n = 73, 79.3%), and patient proportion with Gastric Cleanness Grade C was most found in group 1 (n = 72, 65.5%), which was greatly different (P < 0.001). There was no statistically significant difference on the satisfaction scores [immediately 6 (3–8) vs. 6 (1–10) vs. 6 (1-9), P = 0.533; 2 h after 10 (8–10) vs. 10 (10–10) vs. 10 (8-10), P = 0.463]. Conclusion Simethicone solution intake 31–60 min before esophagogastroduodenoscopy can help obtain the best gastric cleanness, which is recommended in clinical practice (registered at ClinicalTrials.gov, NCT03776916 on December 13, 2018).

Environmental problems are usually framed by a repertoire of arguments articulated by a network of individuals (scientists and policymakers) and their affiliated institutions. Given the complexity of this network, it is important to conduct network analyses on both individual and organizational levels to achieve a better understanding of the underlying political structure that influences science-policy communication. Through an empirical study of a policy network related to grassland management in China, our study examines the underlying political structure of the network as well as its political impact on the problem-framing processes. The analysis reveals that political polarization and power imbalances in the network, the product of existing institutional arrangements, have confined the framing of environmental problems to specific areas and impeded the development of comprehensive policies.