• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.11
• /
• pp.281-290
• /
• 2020

With the spread of smartphones, services that want to use personalized data are increasing. In particular, healthcare-related services deal with a variety of data, and data visualization techniques are used to effectively show this. As data visualization techniques are used, interactions in visualization are also naturally emphasized. In the PC environment, since the interaction for data visualization is performed with a mouse, various filtering for data is provided. On the other hand, in the case of interaction in a mobile environment, the screen size is small and it is difficult to recognize whether or not the interaction is possible, so that only limited visualization provided by the app can be provided through a button touch method. In order to overcome the limitation of interaction in such a mobile environment, we intend to enable data visualization interactions through conversations with chatbots so that users can check individual data through various visualizations. To do this, it is necessary to convert the user's query into a query and retrieve the result data through the converted query in the database that is storing data periodically. There are many studies currently being done to convert natural language into queries, but research on converting user queries into queries based on visualization has not been done yet. Therefore, in this paper, we will focus on query generation in a situation where a data visualization technique has been determined in advance. Supported interactions are filtering on task x-axis values and comparison between two groups. The test scenario utilized data on the number of steps, and filtering for the x-axis period was shown as a bar graph, and a comparison between the two groups was shown as a line graph. In order to develop a natural language processing model that can receive requested information through visualization, about 15,800 training data were collected through a survey of 1,000 people. As a result of algorithm development and performance evaluation, about 89% accuracy in classification model and 99% accuracy in query generation model was obtained.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.9
• /
• pp.103-115
• /
• 2014

In this paper, we propose UniBAS(Unified Bug Analysis System) to provide a unified repository model by integrating the extracted data from the heterogeneous bug tracking systems. The UniBAS reduces the cost and complexity of the MSR(Mining Software Repositories) research process and enables the researchers to focus on their logics rather than the tedious and repeated works such as extracting repositories, processing data and building analysis models. Additionally, the system not only extracts the data but also automatically generates database tables, views and stored procedures which are required for the researchers to perform query-based analysis easily. It can also generate various types of exported files for utilizing external analysis tools or managing research data. A case study of detecting duplicate bug reports from the Firfox project of the Mozilla site has been performed based on the UniBAS in order to evaluate the usefulness of the system. The results of the experiments with various algorithms of natural language processing and flexible querying to the automatically extracted data also showed the effectiveness of the proposed system.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.6
• /
• pp.1443-1452
• /
• 1996

In this paper, we propose a semantic similarity measure for reusable software components, which aims to provide the automatic classification process of reusable to be stored in the structure of a software library, and to provide an efficient retrieval method of the software components satisfying the user's requirements. We have identified the facets to represent component characteristics by extracting information from the component descriptions written in a natural language, composed the software component identifiers from the automatically extracted terms corresponding to each facets, and stored them which the components in the nearest locations according to the semantic similarity of the classified components. In order to retrieve components satisfying user's requirements, we measured a semantic similarity between the queries and the stored components in the software library. As a result of using the semantic similarity to retrieve reusable components, we could not only retrieve the set of components satisfying user's queries. but also reduce the retrieval time of components of user's request. And we further improve the overall retrieval efficiency by assigning relevance ranking to the retrieved components according to the degree of query satisfaction.

• Journal of Digital Convergence
• /
• v.11 no.1
• /
• pp.225-236
• /
• 2013

The voice recognition has been made continuously. Now, this technology could support even natural language beyond recognition of isolated words. Interests for the voice recognition was boosting after the Siri, I-phone based voice recognition software, was presented in 2010. There are some occasions implemented voice enabled services using Korean voice recognition softwares, but their accuracy isn't accurate enough, because of background noise and lack of control on voice related features. In this paper, we propose a sort of multi-purpose preprocessor to improve this situation. This supports Keyword spotting in the continuous speech in addition to noise filtering function. This should be independent of any voice recognition software and it can extend its functionality to support continuous speech by additionally identifying the pre-predicate and the post-predicate in relative to the spotted keyword. We get validation about noise filter effectiveness, keyword recognition rate, continuous speech recognition rate by experiments.

• Journal of the Korea Convergence Society
• /
• v.9 no.10
• /
• pp.45-53
• /
• 2018

Recently, studies about bilingual word embedding have been gaining much attention. However, bilingual word embedding with Korean is not actively pursued due to the difficulty in obtaining a sizable, high quality corpus. Local embeddings that can be applied to specific domains are relatively rare. Additionally, multi-word vocabulary is problematic due to the lack of one-to-one word-level correspondence in translation pairs. In this paper, we crawl 868,163 paragraphs from a Korean-English law corpus and propose three mapping strategies for word embedding. These strategies address the aforementioned issues including multi-word translation and improve translation pair quality on paragraph-aligned data. We demonstrate a twofold increase in translation pair quality compared to the global bilingual word embedding baseline.

• The Journal of the Korea Contents Association
• /
• v.15 no.10
• /
• pp.636-646
• /
• 2015

In information society, the need to detect document duplication and plagiarism is increasing. Many studies have progressed to meet such need, but there are limitations in increasing document duplication detection quality due to technological problem of natural language processing. Recently, some studies tried to increase the quality by applying syntatic-semantic analysis technique. But, the studies have the problem comparing syntactic-semantic trees. This paper develops a syntactic-semantic tree comparator, designs and implements a discriminator of similar documents using the comparator. To evaluate the system, we analyze the correlation between human discrimination and system discrimination with the comparator. This analysis shows that the proposed discrimination has good performance. We need to define the document type and improve the processing technique appropriate for each type.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.3
• /
• pp.61-67
• /
• 2009

The proliferation of the Internet grows, according to electronic documents, along with increasing importance of technology in information retrieval. This research is possible to build a more efficient and accurate knowledge-base with unstructured text documents from the Web using to extract knowledge of the core meaning of LGG (Local Grammar Graph). We have built a ontology based on OWL(Web Ontology Language) using the areas of particular stocks up/down patterns created by the extraction and grammar patterns. It is possible for the user can search for meaning and quality of information about the user wants.

• Annual Conference on Human and Language Technology
• /
• 2002.10e
• /
• pp.85-91
• /
• 2002

최근 정보 추출, 질의응답 시스템 등의 고정밀 자연어처리 어플리케이션이 부각됨에 따라 개체명 인식의 중요성이 더욱 커지고 있다. 이러한 개체명 인식을 위한 학습에는 대용량의 어휘자료를 필요로 하기 때문에 충분한 학습 데이터, 즉 개체명 태그가 부착된 충분한 코퍼스가 제공되지 못하는 경우 자료희귀문제(data sparseness problem)로 인하여 목적한 효과를 내지 못하는 경우가 않다. 그러나 태그가 부착된 코퍼스를 생성하는 일은 시간과 인력이 많이 드는 힘든 작업이다. 최근 인터넷의 발전으로 웹 데이터는 그 양이 매우 많으며, 습득 또한 웹 검색 엔진을 사용해서 자동으로 모음으로써 다량의 말뭉치를 모으는 것이 매우 용이하다. 따라서 최근에는 웹을 무한한 언어자원으로 보고 웹에서 필요한 언어자원을 자동으로 뽑는 연구가 활발히 진행되고 있다. 본 연구는 이러한 연구의 첫 시도로 웹으로부터 다량의 원시(raw) 코퍼스를 얻어 개체명 태깅 학습을 위한 태그 부착 코퍼스를 자동으로 생성하고 이렇게 생성된 말뭉치를 개체면 태깅 학습에 적용하는 비교 실험을 통해 수집된 말뭉치의 유효성을 검증하고자 한다. 향후에는 자동으로 웹으로부터 개체 명 태깅 규칙과 패턴을 뽑아내어 실제 개체명 태거를 빨리 개발하여 유용하게 사용할 수 있다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2004.05b
• /
• pp.552-556
• /
• 2004

This paper surveys the design of the adaptive information filtering agents to retrieve the useful information within a large scale database. As the information retrieval through the Internet is generalized, it is necessary to extract the useful information satisfied the user's request condition to reduce the seeking time. For the first, this module is designed by the Rough reduct to generate the reduced minimal knowledge database considered the users natural query language in a large scale knowledge database, and also it is executed the soft computing by the fuzzy composite processing to operate the uncertain value of the reduced schema domain.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.329-333
• /
• 2022

상호참조해결은 주어진 문서에서 상호참조해결 대상이 되는 멘션(mention)을 식별하고, 동일한 개체(entity)를 의미하는 멘션들을 찾아 그룹화하는 자연어처리 태스크이다. 최근 상호참조해결에서는 BERT를 이용하여 단어의 문맥 표현을 얻은 후, 멘션 탐지와 상호참조해결을 동시에 진행하는 End-to-End 모델이 주로 연구가 되었다. 그러나 End-to-End 방식으로 모델을 수행하기 위해서는 모든 스팬을 잠재적인 멘션으로 간주해야 되기 때문에 많은 메모리가 필요하고 시간 복잡도가 상승하는 문제가 있다. 본 논문에서는 서브 토큰을 다시 단어 단위로 매핑하여 상호참조해결을 수행하는 워드 레벨 상호참조해결 모델을 한국어에 적용하며, 한국어 상호참조해결의 특징을 반영하기 위해 워드 레벨 상호참조해결 모델의 토큰 표현에 개체명 자질과 의존 구문 분석 자질을 추가하였다. 실험 결과, ETRI 질의응답 도메인 평가 셋에서 F1 69.55%로, 기존 End-to-End 방식의 상호참조해결 모델 대비 0.54% 성능 향상을 보이면서 메모리 사용량은 2.4배 좋아졌고, 속도는 1.82배 빨라졌다.