• 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.

• Korean Journal of Soil Science and Fertilizer
• /
• v.25 no.3
• /
• pp.202-212
• /
• 1992

This study reports on the genesis and mineralogical characteristics of the clay minerals in the soils derived from the five major parent rocks of granite, granite-gneiss, limestone, shale, and basalt in Korea. The investigation on the mineralogical aspects of primary and secondary minerals of the rocks and coarse fractions in the soils have been already reported. In this report, the identification of clay minerals in the soil clay fractions was done through the analyses of chemical, X-ray diffraction, and thermal methods. The studies showed clearly that much of the clay minerals was evolved by the weathering of primary minerals and some were further developed by the transformation of secondary minerals. Cation exchange capacity(CEC) of the clay fractions increased with higher amotunts of vermiculite, chlorite, and illite, however, decreased with higher hydroxy octahedral sheet within the interlayer spaces of vermiculite even if dominant clay with vermiculite. Feldspars in the granite and granite-gneiss might be completely transformed to kaolin mineral, Illite, chlolrite, and vermiculite formed by the alteration of micas, amphibole, augite, and primary chlorile seem to be subsequently transformed to the mixed layer minerals such as illite/vermiculite, illite/chlorite, and chlorite/vermiculite. These weathering products may be ultimately transformed into kaolin minerals. The smectite minerals in the clay fractions of the soils developed on the limestone are considerably present and they seem to be formed directly by the precipitation from high Mg solution and/or by the transformation of vermiculite from micas and chlorite in the parent materials. Abundant presence of illite in the soil clays developed on the shale is considered to have inherited from the fine particles and more resistant hydrous muscovite. The weathering sequences of the hydrous muscovite were as follows according to the degree of soil development ; hydrous muscovite ${\rightarrow}$ illite/vermiculite mixed layer(Inceptisols, Daegu series) and hydrous muscovite ${\rightarrow}$ illite/vermiculite mixed layer ${\rightarrow}$ vermiculite ${\rightarrow}$ kaolin mineral(Alfisols, Buyeo series). The plagioclase in the basalt might be mostly weathered to kaolin minerais. The augite in the basalt is likely to be transformed through progressive stage of weathering, augite ${\rightarrow}$ chlorite ${\rightarrow}$ chlorote/vermiculite mixed layer ${\rightarrow}$ vermiculite ${\rightarrow}$ kaolin. Another weathering sequence of augite could be expected, augite ${\rightarrow}$ chlorite ${\rightarrow}$ illite by the presence of illite and illite/vermiculite mixed layer in the clay fractions. Vermiculite and gibbsite were quantified from thermogravimetry(TG) and kaolin minerals, from both TG and differerential thermal analysis (DTA). Vermiculite in Jangseong series from the limestone was the dominant clay mineral of 21.7 percent and had a range in the order of 9.2 percent in Buyeo series to 5.4 percent in Daegu series from the shale. The rest soils ranged from 8.8 to 28.3 percent. Kaolin minerals were the dominant clay mineral of 32.7 percent in Asan series from the granite-gneiss and Gueom series of 32.0 percent from the basalt. The soils from the limestone ranged from 9.4 to 14.9 percent. The rest soils ranged from 8.9 to 28.6 percent. Gibbsite were 3.9 and 2.3 percent for Weoljeong and Chahang series from the granite, respectively. In Asan and Cheongsan series from the giranite-gneiss were 1.4 and 4.5 percent, respectively, and 3.6 percent in Jangpa series from the basalt.