• Journal of KIISE:Databases
• /
• v.32 no.2
• /
• pp.204-218
• /
• 2005

XML has rapidly emerged as the standard for the interchange of data in numerous application areas. To support for efficient queries against XML data, many query languages have been designed. The query languages require the users to know the structure of the XML documents and specify search conditions on the structure. This path-based query against XML documents is a natural consequence of the hierarchical structure of XML. However, it is also desirable to allow the users to formulate no path queries against XML documents, to complement the current path-based queries. In this paper, we design a query expression capable of querying without knowledge about the structure of XML documents, and develop a query processor to evaluate no path queries.

• 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.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.4
• /
• pp.145-152
• /
• 2020

MRC (Machine reading comprehension) is the AI NLP task that predict the answer for user's query by understanding of the relevant document and which can be used in automated consult services such as chatbots. Recently, the BERT (Pre-training of Deep Bidirectional Transformers for Language Understanding) model, which shows high performance in various fields of natural language processing, have two phases. First phase is Pre-training the big data of each domain. And second phase is fine-tuning the model for solving each NLP tasks as a prediction. In this paper, we have made the Patent MRC dataset and shown that how to build the patent consultation training data for MRC task. And we propose the method to improve the performance of the MRC task using the Pre-trained Patent-BERT model by the patent consultation corpus and the language processing algorithm suitable for the machine learning of the patent counseling data. As a result of experiment, we show that the performance of the method proposed in this paper is improved to answer the patent counseling query.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.4 s.42
• /
• pp.271-281
• /
• 2006

Due to the development of Internet, number of online documents and the amount of web services are increasing dramatically. However, there are several procedures required, before you actually find what you were looking for. These procedures are necessary to Internet users, but it takes time to search. As a method to systematize and simplify this repetitive job, this paper suggests a DotQuery based interactive search agent. This agent enables a user to search, from his computer, a plenty of information through the DotQuery service. which includes natural languages. and it executes several procedures required instead. This agent also functions as a plug-in service within general web browsers such as Internet Explorer and decodes the DotQuery service. Then it analyzes the DotQuery from a user through its own program and acquires service results through multiple browsers of its own.

• Annual Conference on Human and Language Technology
• /
• 1998.10c
• /
• pp.65-72
• /
• 1998

인터넷 정보 검색에서 이용자들이 주로 사용하는 질의는 2-3개의 용어로 이루어진 짧은 질의이다. 또만 동음이의어를 갖는 용어를 사용하기도 한다. 짧은 질의를 처리하는 일반적인 방법은 시소러스[8]나 Wordnet[1]을 이용한 질의 확장이다. 그러나 시소러스나 Wordnet과 같은 지식 베이스는 구축하기가 용이하지 않으며, 도메인 종속적인 면과 단어의 회귀(sparseness) 문제를 극복하기 어려운 단점이 있다. 또한 동음이의어 용어로 인하여 검색의 정확성이 털어지는 문제점이 있다. 한편, 사용자의 질의를 주의 깊게 살펴보면, 질의로부터 관련 용어 분류 정보를 추출할 수 있다. 본 논문은 사용자의 질의가 관련 용어 분류 정보에 의해 유기적으로 관계를 가지고 있다는 사실에 기인하여 관련 용어 분류 정보에 따라 자동으로 용어 확장 및 한정을 수행하며 적절한 용어 가중치를 부여하는 자동 질의 용어 정련기를 제안한다. 자동 질의 용어 정련기는 용어의 확장, 한정 및 가중치 부여를 통하여 사용자의 정보 검색 요구를 명확히 하여 검색의 정확성을 향상시킨다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.04a
• /
• pp.1058-1061
• /
• 2012

최근 웹을 기반으로 한 계속적인 기술 발전에 따라 의사결정에 필요한 데이터의 요구는 점점 다양해지고 있으며 다양한 요구를 효과적으로 대응하기 위해 데이터 추출 방법에 대한 연구도 지속적으로 이루어지고 있다. 이에 본 논문에서는 자연어를 통해 사용자가 쉽게 원하는 자료를 추출 할 수 있는 방법론을 연구 하였다. 자연어 처리 기술에 대한 연구는 여러 방면에서 이루어지고 있는데 그 중에서도 본 논문에서는 기존의 자연어 처리 연구를 바탕으로 크게 3가지 형태로 연구 진행 하였다. 사용자가 입력한 정보를 바탕으로 유추하여 자연어를 처리하거나 이후 진행될 검색을 선 예측 하는 방법과 사용자 별로 검색되는 자연어를 통해 연관 관계를 설정하여 사용자에게 예측검색을 유도하는 방법 그리고 의사 결정을 위해 구축된 데이터베이스 스키마 정보를 이용하여 사용자가 쉽게 질의 문을 생성할 수 있도록 하는 방법론 연구이다. 본 논문을 통해 연구된 내용은 실제 구축하여 진행 하였고, 연구결과로 생성된 질의 문이 효과적으로 시스템에서 처리 되는 과정에 대한 연구도 함께 진행하고 검증하였다.

• Journal of Advanced Information Technology and Convergence
• /
• v.10 no.2
• /
• pp.139-151
• /
• 2020

Entity name recognition is a part of information extraction that extracts entity names from documents and classifies the types of extracted entity names. Entity name recognition technologies are widely used in natural language processing, such as information retrieval, machine translation, and query response systems. Various deep learning-based models exist to improve entity name recognition performance, but studies that compared and analyzed these models on Korean data are insufficient. In this paper, we compare and analyze the performance of CRF, LSTM-CRF, BiLSTM-CRF, and BERT, which are actively used to identify entity names using Korean data. Also, we compare and evaluate whether embedding models, which are variously used in recent natural language processing tasks, can affect the entity name recognition model's performance improvement. As a result of experiments on patent data and Korean corpus, it was confirmed that the BiLSTM-CRF using FastText method showed the highest performance.

• Journal of Information Science Theory and Practice
• /
• v.2 no.1
• /
• pp.6-21
• /
• 2014

This paper proposes a novel knowledge extraction system, TAKES (Two-step Approach for Knowledge Extraction System), which integrates advanced techniques from Information Retrieval (IR), Information Extraction (IE), and Natural Language Processing (NLP). In particular, TAKES adopts a novel keyphrase extraction-based query expansion technique to collect promising documents. It also uses a Conditional Random Field-based machine learning technique to extract important biological entities and relations. TAKES is applied to biological knowledge extraction, particularly retrieving promising documents that contain Protein-Protein Interaction (PPI) and extracting PPI pairs. TAKES consists of two major components: DocSpotter, which is used to query and retrieve promising documents for extraction, and a Conditional Random Field (CRF)-based entity extraction component known as FCRF. The present paper investigated research problems addressing the issues with a knowledge extraction system and conducted a series of experiments to test our hypotheses. The findings from the experiments are as follows: First, the author verified, using three different test collections to measure the performance of our query expansion technique, that DocSpotter is robust and highly accurate when compared to Okapi BM25 and SLIPPER. Second, the author verified that our relation extraction algorithm, FCRF, is highly accurate in terms of F-Measure compared to four other competitive extraction algorithms: Support Vector Machine, Maximum Entropy, Single POS HMM, and Rapier.

• Annual Conference on Human and Language Technology
• /
• 2003.10d
• /
• pp.214-218
• /
• 2003

질의응답 시스템은 인터넷과 같은 실용적 환경에서 사용될 경우, 실제 사용자의 질의는 다양한 유형으로 나타나게 된다. 따라서 실용적인 시스템에서 사용되는 질의는 문장의 형태나 단어의 쓰임에 관계없이 같은 의도를 가진 질의를 같은 유형으로 분류할 수 있는 의문형 문장패턴을 태깅하여 다양한 형태의 자연어로 기술된 문서에서 원하는 응답으로 처리할 수 있는 질의 응답 시스템은 정보 검색 시스템으로서의 가능성을 보여준다.

• Annual Conference on Human and Language Technology
• /
• 2002.10e
• /
• pp.223-227
• /
• 2002

자연언어 질의 문장으로부터 검색어로 사용될 질의어의 추출 및 질의어 가중치를 계산하기 위하여 질의 문장들의 유형을 분석하였으며, 질의어 구문의 특성에 따라 용어들의 가중치를 계산하는 방법을 제안하였다. 용어의 가중치를 부여할 때 띄어쓴 복합명사와 접속 관계 등에 의해 연결된 명사구는 질의어 가중치를 동등하게 적용할 필요가 있다. 질의 문장에서 가중치가 동등하게 적용되는 명사구를 인식하기 위한 목적으로 구현된 명사구 chunking을 수행한 후에 각 용어들에 대한 질의어 가중치를 계산한다. 질의어 가중치를 계산하기 위하여 용어의 유형, 질의 구문의 특성, 문서 유형을 지칭하는 용어, 조사 유형, 용어의 길이 등에 따라 가중치를 조절하는 방법을 사용한다. 용어유형에 의한 가중치 계산은 추출된 용어의 품사 정보와 전문 용어 사전, 부사성 명사 사전을 이용하였다.