• Journal of the Korean Society for Library and Information Science
• /
• 제57권1호
• /
• pp.93-114
• /
• 2023

Information extraction can facilitate the intensive analysis of documents by providing semantic triples which consist of named entities and their relations recognized in the texts. However, most of the research so far has been carried out separately for named entity recognition and relation extraction as individual studies, and as a result, the effective performance evaluation of the entire information extraction systems was not performed properly. This paper introduces two models of end-to-end information extraction that can extract various entity names in clinical records and their relationships in the form of semantic triples, namely pipeline and joint models and compares their performances in depth. The pipeline model consists of an entity recognition sub-system based on bidirectional GRU-CRFs and a relation extraction module using multiple encoding scheme, whereas the joint model was implemented with a single bidirectional GRU-CRFs equipped with multi-head labeling method. In the experiments using i2b2/VA 2010, the performance of the pipeline model was 5.5% (F-measure) higher. In addition, through a comparative experiment with existing state-of-the-art systems using large-scale neural language models and manually constructed features, the objective performance level of the end-to-end models implemented in this paper could be identified properly.

• Journal of KIISE
• /
• 제44권11호
• /
• pp.1138-1148
• /
• 2017

Topic extraction is a technology that automatically extracts a set of topics from a set of documents, and this has been a major research topic in the area of natural language processing. Representative topic extraction methods include Latent Dirichlet Allocation (LDA) and word clustering-based methods. However, there are problems with these methods, such as repeated topics and mixed topics. The problem of repeated topics is one in which a specific topic is extracted as several topics, while the problem of mixed topic is one in which several topics are mixed in a single extracted topic. To solve these problems, this study proposes a method to extract topics using an LDA that is robust against the problem of repeated topic, going through the steps of separating and merging the topics using the similarity between words to correct the extracted topics. As a result of the experiment, the proposed method showed better performance than the conventional LDA method.

• Journal of the Korean Society for Library and Information Science
• /
• 제39권2호
• /
• pp.287-304
• /
• 2005

The goal of this research is to evaluate the usability of visually browsing the automatically extracted information. A domain-independent information extraction system was used to extract information from news type texts to populate the visually browasable knowledge base. The information extraction system automatically generated Concept-Relation-Concept triples by applying various Natural Language Processing techniques to the text portion of the news articles. To visualize the information stored in the knowledge base, we used PersoanlBrain to develop a visualization portion of the user interface. PersonalBrain is a hyperbolic information visualization system, which enables the users to link information into a network of logical associations. To understand the usability of the visually browsable knowledge base, IS test subjects were observed while they use the visual interface and also interviewed afterward. By applying a qualitative test data analysis method. a number of usability Problems and further research directions were identified.

• KIPS Transactions on Software and Data Engineering
• /
• 제12권8호
• /
• pp.371-380
• /
• 2023

Relation extraction is to extract relationships between named entities from text. Traditionally, relation extraction methods only extract relations between predetermined subject and object entities. However, in end-to-end relation extraction, all possible relations must be extracted by considering the positions of the subject and object for each pair of entities, and so this method uses time and resources inefficiently. To alleviate this problem, this paper proposes a method that sets directions based on the positions of the subject and object, and extracts relations according to the directions. The proposed method utilizes existing relation extraction data to generate direction labels indicating the direction in which the subject points to the object in the sentence, adds entity position tokens and entity type to sentences to predict the directions using a pre-trained language model (KLUE-RoBERTa-base, RoBERTa-base), and generates representations of subject and object entities through probabilistic crossover operation. Then, we make use of these representations to extract relations. Experimental results show that the proposed model performs about 3 ~ 4%p better than a method for predicting integrated labels. In addition, when learning Korean and English data using the proposed model, the performance was 1.7%p higher in English than in Korean due to the number of data and language disorder and the values of the parameters that produce the best performance were different. By excluding the number of directional cases, the proposed model can reduce the waste of resources in end-to-end relation extraction.

• Journal of Korea Society of Industrial Information Systems
• /
• 제7권5호
• /
• pp.183-189
• /
• 2002

In this paper, we propose an algorithm to extract the E-mail address in calling card images. Firstly, text regions are separated from background. in the image. To do this, the properties of e-mail addresses and the texture features in the image is used. And then, each text region is explored to find the candidates of e-mail region. Finally, each candidate is divided into characters to find at-symbol(@), that is, e-mail region. The experimental results show hit-ratio over 93.3％ for the various kind of calling cards containing different fonts, background images, caricatures.

• Journal of Korean Medical classics
• /
• 제33권4호
• /
• pp.67-81
• /
• 2020

Objectives : This research aims to suggest a automatic data extract method for herbal formula combinations from medical classics' texts. Methods : This research was carried out by using Access of Microsoft Office 365 in Windows 10 of Microsoft. The subject text for extraction was 『Euijongsonik』. Using data sets of herb and dosage terminology, herbal medicinals and their dosages were extracted. Afterwards, using the position value of the character string, the formula combinations were automatically extracted. Results :The PC environment of this research was Intel Core i7-1065G7 CPU 1.30GHz, with 8GB of RAM and a Windows 10 64bit operation system. Out of 6,115 verses, 19,277 herb-dosage combinations were extracted. Conclusions : In this research, it was demonstrated that in the case of classical texts that are available as data, knowledge on herbal medicine could be extracted without human or material resources. This suggests an applicability of classical text knowledge to clinical practice.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• 제13권2호
• /
• pp.27-33
• /
• 2014

This paper proposes a gradation image processing method for the development of a Road Sign Recognition Platform (RReP), which aims to facilitate the rapid and accurate management and surveying of approximately 160,000 road signs installed along the highways, national roadways, and local roads in the cities, districts (gun), and provinces (do) of Korea. RReP is based on GPS(Global Positioning System), IMU(Inertial Measurement Unit), INS(Inertial Navigation System), DMI(Distance Measurement Instrument), and lasers, and uses an imagery information collection/classification module to allow the automatic recognition of signs, the collection of shapes, pole locations, and sign-type data, and the creation of road sign registers, by extracting basic data related to the shape and sign content, and automated database design. Image division and merging, which were applied in this study, produce superior results compared with local binarization method in terms of speed. At the results, larger texts area were found in images, the accuracy of text recognition was improved when images had been gradated. Multi-threshold values of natural scene images are used to improve the extraction rate of texts and figures based on pattern recognition.

• The Journal of Information Systems
• /
• 제28권3호
• /
• pp.105-121
• /
• 2019

Purpose One of the reasons for the expansion of information systems in the enterprise is the increased efficiency of data analysis. In particular, the rapidly increasing data types which are complex and unstructured such as video, voice, images, and conversations in and out of social networks. The purpose of this study is the customer needs analysis from customer voices, ie, text data, in the web environment.. Design/methodology/approach As previous study results, the word frequency of the sentence is extracted as a word that interprets the sentence has better affects than frequency analysis. In this study, we applied the TF-IDF method, which extracts important keywords in real sentences, not the TF method, which is a word extraction technique that expresses sentences with simple frequency only, in Korean language research. We visualized the two techniques by cluster analysis and describe the difference. Findings TF technique and TF-IDF technique are applied for Korean natural language processing, the research showed the value from frequency analysis technique to semantic analysis and it is expected to change the technique by Korean language processing researcher.

• Genomics & Informatics
• /
• 제17권2호
• /
• pp.15.1-15.7
• /
• 2019

Automatically detecting mentions of pharmaceutical drugs and chemical substances is key for the subsequent extraction of relations of chemicals with other biomedical entities such as genes, proteins, diseases, adverse reactions or symptoms. The identification of drug mentions is also a prior step for complex event types such as drug dosage recognition, duration of medical treatments or drug repurposing. Formally, this task is known as named entity recognition (NER), meaning automatically identifying mentions of predefined entities of interest in running text. In the domain of medical texts, for chemical entity recognition (CER), techniques based on hand-crafted rules and graph-based models can provide adequate performance. In the recent years, the field of natural language processing has mainly pivoted to deep learning and state-of-the-art results for most tasks involving natural language are usually obtained with artificial neural networks. Competitive resources for drug name recognition in English medical texts are already available and heavily used, while for other languages such as Spanish these tools, although clearly needed were missing. In this work, we adapt an existing neural NER system, NeuroNER, to the particular domain of Spanish clinical case texts, and extend the neural network to be able to take into account additional features apart from the plain text. NeuroNER can be considered a competitive baseline system for Spanish drug and CER promoted by the Spanish national plan for the advancement of language technologies (Plan TL).

• Child Health Nursing Research
• /
• 제29권3호
• /
• pp.182-194
• /
• 2023

Purpose: This study analyzed research trends in infant and toddler rearing behavior among family caregivers over a 10-year period (2010-2021). Methods: Text network analysis and topic modeling were employed on data collected from relevant papers, following the extraction and refinement of semantic morphemes. A semantic-centered network was constructed by extracting words from 2,613 English-language abstracts. Data analysis was performed using NetMiner 4.5.0. Results: Frequency analysis, degree centrality, and eigenvector centrality all revealed the terms ''scale," ''program," and ''education" among the top 10 keywords associated with infant and toddler rearing behaviors among family caregivers. The keywords extracted from the analysis were divided into two clusters through cohesion analysis. Additionally, they were classified into two topic groups using topic modeling: "program and evaluation" (64.37%) and "caregivers' role and competency in child development" (35.63%). Conclusion: The roles and competencies of family caregivers are essential for the development of infants and toddlers. Intervention programs and evaluations are necessary to improve rearing behaviors. Future research should determine the role of nurses in supporting family caregivers. Additionally, it should facilitate the development of nursing strategies and intervention programs to promote positive rearing practices.