• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.165-166
• /
• 2010

Noun extraction is to find all nouns presented in the document, Korean information retrieval uses noun as index terms or keywords of representing the document. In this paper, we proposes the method of keyword extraction using pre-built dictionary. This method reduces the execution time by reducing unnecessary operations. And noun, even large documents without affecting significantly the accuracy, can be extracted. This paper proposed noun extraction method using the appearance characteristics of the noun and keyword extraction method using unsupervised learning techniques.

• Journal of Information Processing Systems
• /
• v.8 no.4
• /
• pp.693-712
• /
• 2012

The paper presents three machine learning based keyphrase extraction methods that respectively use Decision Trees, Na$\ddot{i}$ve Bayes, and Artificial Neural Networks for keyphrase extraction. We consider keyphrases as being phrases that consist of one or more words and as representing the important concepts in a text document. The three machine learning based keyphrase extraction methods that we use for experimentation have been compared with a publicly available keyphrase extraction system called KEA. The experimental results show that the Neural Network based keyphrase extraction method outperforms two other keyphrase extraction methods that use the Decision Tree and Na$\ddot{i}$ve Bayes. The results also show that the Neural Network based method performs better than KEA.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.771-791
• /
• 2022

Protein-protein interaction (PPI) extraction from original text is important for revealing the molecular mechanism of biological processes. With the rapid growth of biomedical literature, manually extracting PPI has become more time-consuming and laborious. Therefore, the automatic PPI extraction from the raw literature through natural language processing technology has attracted the attention of the majority of researchers. We propose a PPI extraction model based on the large pre-trained language model and adversarial training. It enhances the learning of semantic and syntactic features using BioBERT pre-trained weights, which are built on large-scale domain corpora, and adversarial perturbations are applied to the embedding layer to improve the robustness of the model. Experimental results showed that the proposed model achieved the highest F1 scores (83.93% and 90.31%) on two corpora with large sample sizes, namely, AIMed and BioInfer, respectively, compared with the previous method. It also achieved comparable performance on three corpora with small sample sizes, namely, HPRD50, IEPA, and LLL.

• Journal of Industrial Convergence
• /
• v.13 no.2
• /
• pp.45-54
• /
• 2015

This Study aims to analyze the factors for the success of commercialization of the facial extraction and recognition image security information system of the domestic companies in Korea. As the results of the analysis, the internal factors for the success of commercialization of the facial extraction and recognition image security information system of the company were found to include (1) Holding of technology for close range facial recognition, (2) Holding of several facial recognition related patents, (3) Preference for the facial recognition security system over the fingerprint recognition and (4) strong volition of the CEO of the corresponding company. On the other hand, the external environmental factors for the success were found to include (1) Extensiveness of the market, (2) Rapid growth of the global facial recognition market, (3) Increased demand for the image security system, (4) Competition in securing of the engine for facial extraction and recognition and (5) Selection by the government as one of the 100 major strategic products.

• The Journal of the Korea Contents Association
• /
• v.19 no.11
• /
• pp.278-287
• /
• 2019

Spatial information extraction is to retrieve static and dynamic aspects in natural language text by explicitly marking spatial elements and their relational words. This paper proposes a deep learning approach for spatial information extraction for Korean language using a two-step bidirectional LSTM-CRF ensemble model. The integrated model of spatial element extraction and spatial relation attribute extraction is proposed too. An experiment with the Korean SpaceBank demonstrates the better efficiency of the proposed deep learning model than that of the previous CRF model, also showing that the proposed ensemble model performed better than the single model.

• Journal of KIISE:Software and Applications
• /
• v.31 no.4
• /
• pp.447-456
• /
• 2004

Information extraction is a process of recognizing and fetching particular information fragments from a document. In order to extract information uniformly from many heterogeneous information sources, it is necessary to produce information extraction rules called a wrapper for each source. Previous methods of information extraction can be categorized into manual wrapper generation and automatic wrapper generation. In the manual method, since the wrapper is manually generated by a human expert who analyzes documents and writes rules, the precision of the wrapper is very high whereas it reveals problems in scalability and efficiency In the automatic method, the agent program analyzes a set of example documents and produces a wrapper through learning. Although it is very scalable, this method has difficulty in generating correct rules per se, and also the generated rules are sometimes unreliable. This paper tries to combine both manual and automatic methods by proposing a new method of learning information extraction rules. We adopt the scheme of supervised learning in which a user-interface agent is designed to get information from the user regarding what to extract from a document, and eventually XML-based information extraction rules are generated through learning according to these inputs. The interface agent is used not only to generate new extraction rules but also to modify and extend existing ones to enhance the precision and the recall measures of the extraction system. We have done a series of experiments to test the system, and the results are very promising. We hope that our system can be applied to practical systems such as information-mediator agents.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.111-136
• /
• 2018

In this paper, we propose a methodology to extract answer information about queries from various types of unstructured documents collected from multi-sources existing on web in order to expand knowledge base. The proposed methodology is divided into the following steps. 1) Collect relevant documents from Wikipedia, Naver encyclopedia, and Naver news sources for "subject-predicate" separated queries and classify the proper documents. 2) Determine whether the sentence is suitable for extracting information and derive the confidence. 3) Based on the predicate feature, extract the information in the proper sentence and derive the overall confidence of the information extraction result. In order to evaluate the performance of the information extraction system, we selected 400 queries from the artificial intelligence speaker of SK-Telecom. Compared with the baseline model, it is confirmed that it shows higher performance index than the existing model. The contribution of this study is that we develop a sequence tagging model based on bi-directional LSTM-CRF using the predicate feature of the query, with this we developed a robust model that can maintain high recall performance even in various types of unstructured documents collected from multiple sources. The problem of information extraction for knowledge base extension should take into account heterogeneous characteristics of source-specific document types. The proposed methodology proved to extract information effectively from various types of unstructured documents compared to the baseline model. There is a limitation in previous research that the performance is poor when extracting information about the document type that is different from the training data. In addition, this study can prevent unnecessary information extraction attempts from the documents that do not include the answer information through the process for predicting the suitability of information extraction of documents and sentences before the information extraction step. It is meaningful that we provided a method that precision performance can be maintained even in actual web environment. The information extraction problem for the knowledge base expansion has the characteristic that it can not guarantee whether the document includes the correct answer because it is aimed at the unstructured document existing in the real web. When the question answering is performed on a real web, previous machine reading comprehension studies has a limitation that it shows a low level of precision because it frequently attempts to extract an answer even in a document in which there is no correct answer. The policy that predicts the suitability of document and sentence information extraction is meaningful in that it contributes to maintaining the performance of information extraction even in real web environment. The limitations of this study and future research directions are as follows. First, it is a problem related to data preprocessing. In this study, the unit of knowledge extraction is classified through the morphological analysis based on the open source Konlpy python package, and the information extraction result can be improperly performed because morphological analysis is not performed properly. To enhance the performance of information extraction results, it is necessary to develop an advanced morpheme analyzer. Second, it is a problem of entity ambiguity. The information extraction system of this study can not distinguish the same name that has different intention. If several people with the same name appear in the news, the system may not extract information about the intended query. In future research, it is necessary to take measures to identify the person with the same name. Third, it is a problem of evaluation query data. In this study, we selected 400 of user queries collected from SK Telecom 's interactive artificial intelligent speaker to evaluate the performance of the information extraction system. n this study, we developed evaluation data set using 800 documents (400 questions * 7 articles per question (1 Wikipedia, 3 Naver encyclopedia, 3 Naver news) by judging whether a correct answer is included or not. To ensure the external validity of the study, it is desirable to use more queries to determine the performance of the system. This is a costly activity that must be done manually. Future research needs to evaluate the system for more queries. It is also necessary to develop a Korean benchmark data set of information extraction system for queries from multi-source web documents to build an environment that can evaluate the results more objectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.1
• /
• pp.123-144
• /
• 2014

Wireless sensor networks are generally deployed for specific applications to accomplish certain objectives over a period of time. To fulfill these objectives, it is crucial that the sensor network continues to function for a long time, even if some of its nodes become faulty. Energy efficiency and fault tolerance are undoubtedly the most crucial requirements for the design of an information extraction protocol for any sensor network application. However, most existing software agent based information extraction protocols are incapable of satisfying these requirements because of static agent itineraries and large agent sizes. This paper proposes an Information Extraction protocol based on Multiple software Agents with Dynamic Itineraries (IEMADI), where multiple software agents are dispatched in parallel to perform tasks based on the query assigned to them. IEMADI decides the itinerary for an agent dynamically at each hop using local information. Through mathematical analysis and simulation, we compare the performance of IEMADI with a well known static itinerary based protocol with respect to energy consumption and response time. The results show that IEMADI provides better performance than the static itinerary based protocols.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2007.04a
• /
• pp.379-382
• /
• 2007

Laser scanning technology with high positional accuracy and high density automation will be widely applied in vast range of fields including geomatics. Especially, the development of laser scanning technology enabling long range information extraction is increasing its full use in civil engineering. The purpose of this study is to extract accurate highway geometric information taking the advantages of scanning technology. Fulfilling this goal, the information of target highway's three-dimensional data was obtained through terrestrial laser scanning technology. In accordance with the result from target highway's geometric information extraction using the information above, laser scanning technology showed faster speed and better accuracy on highway geometric information extraction with reduced cost compared to traditional methods.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.196-199
• /
• 2002

We presented the automatic extraction technique of a biological internal organization from full-color continuous images. It was implemented using the localized homogeneousness of color intensity, and also using the continuity between neighboring images. Moreover, we set the "four-level status value" of area condition as a value showing "area possibility. This played important role of preventing a miss-judgement of area definition. These our approach had a beneficial effect on tracking color and shape change of the interest area in continuous extraction. As a resell we succeeded in extraction of mouse's stomach from continuous 50 images.