Recognizing software names in biomedical literature using machine learning

Wei, Qiang; Zhang, Yaoyun; Amith, Muhammad; Lin, Rebecca; Lapeyrolerie, Jenay; Tao, Cui; Xu, Hua

doi:10.1177/1460458219869490

Cited by 8 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Increasingly publishers are providing XML versions of article text, and XML is much more suitable for machine processing, but coverage remains only partial and uneven across domains, especially in combination with open access licensing, requiring contract negotiations. Thus, existing NER in scholarly text are often limited to article abstracts or sections (Ozyurt et al, 2016; Schindler et al, 2020; Wei et al, 2020), rather than enabling full‐scale “distant reading” for bibliometric and text analysis of the literature (Mehta, Bradley, Hancock, & Collins, 2017). While XML is increasingly available from traditional publishers, we think it is unlikely that standardized XML will ever achieve full coverage, especially considering the growth of open access pre‐print and institutional repositories.…”

Section: Related Workmentioning

confidence: 99%

Softcite dataset: A dataset of software mentions in biomedical and economic research publications

Cohoon

Lopez³

et al. 2021

Asso for Info Science & Tech

View full text Add to dashboard Cite

Software contributions to academic research are relatively invisible, especially to the formalized scholarly reputation system based on bibliometrics. In this article, we introduce a gold‐standard dataset of software mentions from the manual annotation of 4,971 academic PDFs in biomedicine and economics. The dataset is intended to be used for automatic extraction of software mentions from PDF format research publications by supervised learning at scale. We provide a description of the dataset and an extended discussion of its creation process, including improved text conversion of academic PDFs. Finally, we reflect on our challenges and lessons learned during the dataset creation, in hope of encouraging more discussion about creating datasets for machine learning use.

show abstract

Section: Related Workmentioning

confidence: 99%

Softcite dataset: A dataset of software mentions in biomedical and economic research publications

Cohoon

Lopez³

et al. 2021

Asso for Info Science & Tech

View full text Add to dashboard Cite

show abstract

“…These features can be used together to improve one extraction model. For example, Wei et al (2020) used the bag-of-word, word shape, morphological information, POS tag, domain knowledge, and word embedding features to optimize the performance of the CRF model in software entity extraction. Besides optimizing the single model, combining different features and models is another method used to acquire better extraction models (Liakata et al, 2012;Liakata & Soldatova, 2008).…”

Section: Statistical Machine Learning-based Extraction Methodsmentioning

confidence: 99%

A review on method entities in the academic literature: extraction, evaluation, and application

Wang

Zhang

2022

Scientometrics

View full text Add to dashboard Cite

In scientific research, the method is an indispensable means to solve scientific problems and a critical research object. With the advancement of sciences, many scientific methods are being proposed, modified, and used in academic literature. The authors describe details of the method in the abstract and body text, and key entities in academic literature reflecting names of the method are called method entities. Exploring diverse method entities in a tremendous amount of academic literature helps scholars understand existing methods, select the appropriate method for research tasks, and propose new methods.Furthermore, the evolution of method entities can reveal the development of a discipline and facilitate knowledge discovery. Therefore, this article offers a systematic review of methodological and empirical works focusing on extracting method entities from full-text academic literature and efforts to build knowledge services using these extracted method entities. Definitions of key concepts involved in this review were first proposed. Based on these definitions, we systematically reviewed the approaches and indicators to extract and evaluate method entities, with a strong focus on the pros and cons of each approach. We also surveyed how extracted method entities are used to build new applications. Finally, limitations in existing works as well as potential next steps were discussed.

show abstract

“…The algorithm was applied to the keyword autocompletion effect to achieve good results. (9) Duanmu and Xing used a remotely supervised method to complete the acquisition and preprocessing of data to reduce errors caused by manual operations. Also, a semi-automatic method of collecting financial KG data was proposed.…”

Section: Literature Reviewmentioning

confidence: 99%

Application of Graph Convolutional Network in the Construction of Knowledge Graph for Higher Mathematics Teaching

Yuan,

Li,

Sun

et al. 2023

Sensors and Materials

View full text Add to dashboard Cite

In this study, we first perform data preprocessing using higher mathematics textbooks and network resources to complete the construction of the dataset extracted from the knowledge of this mathematical discipline in order to study the application of a graph neural network in the knowledge graph (KG) of higher mathematics. Then, the graph convolutional network (GCN) and attention mechanism are introduced, and the relationship extraction model based on attention-guided GCN and the text classification model based on GCN are established, whereby the automatic extraction of higher mathematical knowledge can be realized. Finally, sensors are used to collect data from students' classroom responses, the data layer construction of a subject KG is realized, and the database is used to realize the storage visualization of triples. The results show that on the basis of the text classification model of GCN, higher mathematical knowledge classification is set, providing a reference example for the application of GCN in higher education. The constructed higher mathematics atlas has a total of 2580 triples, which can be used on the higher mathematics visual query platform. The self-built recognizer recognition test set obtains a P-value of 89.16% in the higher mathematics theorem law entity and a P-value of 97.73% in the test question of higher mathematics. Therefore, the GCN model established here can be effective in the construction of higher mathematical KGs.

show abstract

Recognizing software names in biomedical literature using machine learning

Cited by 8 publications

References 16 publications

Softcite dataset: A dataset of software mentions in biomedical and economic research publications

Softcite dataset: A dataset of software mentions in biomedical and economic research publications

A review on method entities in the academic literature: extraction, evaluation, and application

Application of Graph Convolutional Network in the Construction of Knowledge Graph for Higher Mathematics Teaching

Contact Info

Product

Resources

About