Subjects: Computer Science >> Natural Language Understanding and Machine Translation Subjects: Library Science，Information Science >> Automation method and equipment in intelligence process submitted time 2019-10-29
Abstract： Purpose: Move recognition in scientific abstracts is an NLP task of classifying sentences of the abstracts into different types of language unit. To improve the performance of move recognition in scientific abstracts, a novel model of move recognition is proposed that outperforms BERT-Base method. Design: Prevalent models based on BERT for sentence classification often classify sentences without considering the context of the sentences. In this paper, inspired by the BERT's Masked Language Model (MLM), we propose a novel model called Masked Sentence Model that integrates the content and contextual information of the sentences in move recognition. Experiments are conducted on the benchmark dataset PubMed 20K RCT in three steps. And then compare our model with HSLN-RNN, BERT-Base and SciBERT using the same dataset. Findings: Compared with BERT-Base and SciBERT model, the F1 score of our model outperforms them by 4.96% and 4.34% respectively, which shows the feasibility and effectiveness of the novel model and the result of our model comes closest to the state-of-the-art results of HSLN-RNN at present. Research Limitations: The sequential features of move labels are not considered, which might be one of the reasons why HSLN-RNN has better performance. And our model is restricted to dealing with bio-medical English literature because we use dataset from PubMed which is a typical bio-medical database to fine-tune our model. Practical implications: The proposed model is better and simpler in identifying move structure in scientific abstracts, and is worthy for text classification experiments to capture contextual features of sentences. Originality: The study proposes a Masked Sentence Model based on BERT which takes account of the contextual features of the sentences in abstracts in a new way. And the performance of this classification model is significantly improved by rebuilding the input layer without changing the structure of neural networks.
Peer Review Status:
Awaiting Review
Subjects: Library Science，Information Science >> Utilization of Information submitted time 2019-06-27
Abstract： This paper expounds the value orientation and essential connotation of knowledge service in the new information and knowledge environment, and its significance to the transformation of university libraries. This paper analyzes the essential difference between knowledge service and ubiquitous subject service from the perspective of university libraries, and the barriers that university libraries should break through in terms of cognition, theory and practice in order to carry out knowledge services more deeply. It is pointed out that knowledge product is an important form of knowledge service, and the level of knowledge product is the direct embodiment of the library's core value and ability. In addition, this paper gives a clear and systematic explanation and description of the concepts, attributes, types and production principles of knowledge products from a theoretical point of view.
Peer Review Status:Awaiting Review
Subjects: Library Science，Information Science >> Library Science submitted time 2019-03-17
Abstract： The paper sorts out the development trends of the international preprint servers; analyzes the policy trends of preprint servers, funding agencies and journals; brings forth the five policy challenges faced in developing Chinese preprint servers: unclear policy positioning, imperfect policy mechanism, lack of high-level management policies, lack of policy support from journals, and insufficient policy starting point; make four suggestions in the development preprint servers in China. "
Peer Review Status:Awaiting Review
Subjects: Library Science，Information Science >> Library Science submitted time 2019-01-04
Abstract： From the perspective of scientometrics and scientific knowledge map, this paper analyzes the number of research papers, national and regional distribution, research institutions, and research directions in the field of library and information in 72 countries along the "Belt and Road". Provide reference for promoting my country's "One Belt, One Road" strategy and scientific and technological cooperation with countries along the route in the field of library and information.
Peer Review Status:Awaiting Review
Hits
Hits
Downloads
Comment