KA-NER: Knowledge Augmented Named Entity Recognition

Li, Chen-Yang; Wang, Honglie

doi:10.1007/978-981-16-6471-7_5

Cited by 3 publications

(4 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nie, BL. et al proposed a novel knowledge-enhanced named entity recognition model (KA-NER) [11], which combines the named entity recognition model with the a priori knowledge of the knowledge base, and successfully solves the limitation of the traditional model in utilizing the relevant knowledge. Han, PF et al established a corresponding entity database based on the statistical collection of Vietnamese names of people, places and organizations in the Vietnamese corpus [12], then, they deeply analyzed the Vietnamese linguistic properties and combined the establishment of the entity database with the proposal of a new named entity recognition model.…”

Section: Related Workmentioning

confidence: 99%

High-Risk HPV Cervical Lesion Potential Correlations Mining over Large-Scale Knowledge Graphs

Zhou,

Xu,

Wang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Lesion prediction, a very important aspect of cancer disease prediction, is an important marker for patients before they become cancerous. Currently, traditional machine learning methods are gradually applied in disease prediction based on patient vital signs data. Accurate prediction requires a large amount and high quality of data, however, the difficulty in obtaining and incompleteness of electronic medical record (EMR) data leads to certain difficulties in disease prediction by traditional machine learning methods. Secondly, there are many factors that contribute to the development of cervical lesions, some risk factors are directly related to it while others are indirectly related to them. In addition, risk factors have an interactive effect on the development of cervical lesions; it does not occur in isolation, a large-scale knowledge graph is constructed base on the close relationships among risk factors in the literature, and new potential key risk factors are mined based on common risk factors through a subgraph mining method. Then lesion prediction algorithm is proposed to predict the likelihood of lesions in patients base on the set of key risk factors. Experimental results show that the circumvents the problems of large number of missing values in EMR data and discovered key risk factors that are easily ignored but have better prediction effect. Therefore, The method had better accuracy in predicting cervical lesions.

show abstract

Section: Related Workmentioning

confidence: 99%

High-Risk HPV Cervical Lesion Potential Correlations Mining over Large-Scale Knowledge Graphs

Zhou,

Xu,

Wang

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…В последнем случае хорошо работают методы, фиксирующие семантику слов на основе простых текстов и общих особенностей естественного языка. В случае NER в предметной области этого недостаточно [76]. Выявление самих NE и их категорий требует использования информации специфичной для конкретной области.…”

Section: Ner в предметных областяхunclassified

“…В работе [75] предлагается систему, уже обученную для NER, адаптировать к новой предметной области. Другие исследователи [76] строят инструмент на основе базы знаний. Интересно, что в обоих случаях средняя F-мера похожи: 80.3 % и 84.82 % соответственно, но во втором всё-таки выше.…”

Section: Ner в предметных областяхunclassified

Name Entity Recognition Tasks: Technologies and Tools

Lagutina

Vasilyev

Zafievsky

2023

Model. anal. inf. sist.

View full text Add to dashboard Cite

The task of named entity recognition (NER) is to identify and classify words and phrases denoting named entities, such as people, organizations, geographical names, dates, events, terms from subject areas. While searching for the best solution, researchers conduct a wide range of experiments with different technologies and input data. Comparison of the results of these experiments shows a significant discrepancy in the quality of NER and poses the problem of determining the conditions and limitations for the application of the used technologies, as well as finding new solutions. An important part in answering these questions is the systematization and analysis of current research and the publication of relevant reviews. In the field of named entity recognition, the authors of analytical articles primarily consider mathematical methods of identification and classification and do not pay attention to the specifics of the problem itself. In this survey, the field of named entity recognition is considered from the point of view of individual task categories. The authors identified five categories: the classical task of NER, NER subtasks, NER in social media, NER in domain, NER in natural language processing (NLP) tasks. For each category the authors discuss the quality of the solution, features of the methods, problems, and limitations. Information about current scientific works of each category is given in the form of a table for clarity. The review allows us to draw a number of conclusions. Deep learning methods are leading among state-of-the-art technologies. The main problems are the lack of datasets in open access, high requirements for computing resources, the lack of error analysis. A promising area of research in NER is the development of methods based on unsupervised techniques or rule-base learning. Intensively developing language models in existing NLP tools can serve as a possible basis for text preprocessing for NER methods. The article ends with a description and results of experiments with NER tools for Russian-language texts.

show abstract

“…These studies have dealt with data scarcity to some extent; however, as indicated in Table 3, the best performance in specific task performance is still [46]. The recently proposed KA-NER by Nie et al [50] incorporates a relevant knowledge base compared to most current NER models that focus only on contextual content or artificially added features. The KA-NER model performs well on multiple datasets and has a high generalization capability due to the average F1-score of 84.82% achieved by this model on multiple datasets.…”

Section: Named Entity Recognition (Ner)mentioning

confidence: 99%

A Survey of Deep Learning for Electronic Health Records

Chen

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

Medical data is an important part of modern medicine. However, with the rapid increase in the amount of data, it has become hard to use this data effectively. The development of machine learning, such as feature engineering, enables researchers to capture and extract valuable information from medical data. Many deep learning methods are conducted to handle various subtasks of EHR from the view of information extraction and representation learning. This survey designs a taxonomy to summarize and introduce the existing deep learning-based methods on EHR, which could be divided into four types (Information Extraction, Representation Learning, Medical Prediction and Privacy Protection). Furthermore, we summarize the most recognized EHR datasets, MIMIC, eICU, PCORnet, Open NHS, NCBI-disease and i2b2/n2c2 NLP Research Data Sets, and introduce the labeling scheme of these datasets. Furthermore, we provide an overview of deep learning models in various EHR applications. Finally, we conclude the challenges that EHR tasks face and identify avenues of future deep EHR research.

show abstract

KA-NER: Knowledge Augmented Named Entity Recognition

Cited by 3 publications

References 42 publications

High-Risk HPV Cervical Lesion Potential Correlations Mining over Large-Scale Knowledge Graphs

High-Risk HPV Cervical Lesion Potential Correlations Mining over Large-Scale Knowledge Graphs

Name Entity Recognition Tasks: Technologies and Tools

A Survey of Deep Learning for Electronic Health Records

Contact Info

Product

Resources

About