• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.1-3
• /
• 2006

본 논문에서는 기네스 기록과 같은 기록정보 즉, 기록적 가치가 있는 문장에 대한 질의가 들어왔을 경우기록 부사와 정답 유형을 이용하여 정답을 추출하는 시스템에 대해 기술한다. 기록정보는 역사적이고 사실적인 내용으로, 기록부사틀 포함하는 문장을 말한다. 기록부사는 기록정보 내에서 쓰이며 어떤 사실의 기록에 대해 뜻을 명확하게 나타내어주는 한 요소이고, 이것은 해당문장이 기록문장임을 나타내준다. 이는 질의-응답 시스템에서 정답 추출의 중요한 단서로 사용될 수 있다. 질의-응답 시스템은 크게 질의를 분석하는 부분과 정답 문서를 찾는 부분으로 나뉘며, 질의 분석을 통하여 기록부사로 지역정보 그리고 정답유형을 결정한 후 이를 이용하여 후보 문서를 검색, 추출하고 정의문 규칙과 개체명 태깅에 의하여 정답을 추출하게 된다.

• International Journal of Control, Automation, and Systems
• /
• v.5 no.1
• /
• pp.99-103
• /
• 2007

Translation equivalence is very important for bilingual lexicography, machine translation system and cross-lingual information retrieval. Extraction of equivalences from bilingual sentence pairs belongs to data mining problem. In this paper, discriminative learning methods are employed to filter translation equivalences. Discriminative features including translation literality, phrase alignment probability, and phrase length ratio are used to evaluate equivalences. 1000 equivalences randomly selected are filtered and then evaluated. Experimental results indicate that its precision is 87.8% and recall is 89.8% for support vector machine.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.397-400
• /
• 2021

To solve the problem that existing computing methods cannot adequately represent the semantic features of sentences, Siamese TRAT, a semantic feature extraction model based on Transformer encoder is proposed. The transformer model is used to fully extract the semantic information within sentences and carry out deep semantic coding for sentences. In addition, the interactive attention mechanism is introduced to extract the similar features of the association between two sentences, which makes the model better at capturing the important semantic information inside the sentence. As a result, it improves the semantic understanding and generalization ability of the model. The experimental results show that the proposed model can improve the accuracy significantly for the semantic similarity calculation task of English and Chinese, and is more effective than the existing methods.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.235-240
• /
• 2021

구문 트리의 구조적 정보는 문장 수준 관계 추출을 수행하는데 있어 매우 중요한 자질 중 하나다. 기존 관계 추출 연구는 구문 트리에서 최단 의존 경로를 적용하는 방식으로 관계 추출에 필요한 정보를 추출해서 활용했다. 그러나 이런 트리 가지치기 기반의 정보 추출은 관계 추출에 필요한 어휘 정보를 소실할 수도 있다는 문제점이 존재한다. 본 논문은 이 문제점을 해소하기 위해 개체 중심으로 구문 트리를 재구축하고 모든 노드의 정보를 관계 추출에 활용하는 모델을 제안한다. 제안 모델은 TACRED에서 F1 점수 74.9 %, KLUE-RE 데이터셋에서 72.0%로 가장 높은 성능을 보였다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.12
• /
• pp.988-992
• /
• 2009

In this paper, we attempted to extract binary relations between terminologies using composite kernels consisting of convolution parse tree kernels and WordNet verb synset vector kernels which explain the semantic relationships between two entities in a sentence. In order to evaluate the performance of our system, we used three domain specific test collections. The experimental results demonstrate the superiority of our system in all the targeted collection. Especially, the increase in the effectiveness on KREC 2008, 8% in F1, shows that the core contexts around the entities play an important role in boosting the entire performance of relation extraction.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.1-25
• /
• 2020

Sentiment Analysis (SA) is a Natural Language Processing (NLP) task that analyzes the sentiments consumers or the public feel about an arbitrary object from written texts. Furthermore, Aspect-Based Sentiment Analysis (ABSA) is a fine-grained analysis of the sentiments towards each aspect of an object. Since having a more practical value in terms of business, ABSA is drawing attention from both academic and industrial organizations. When there is a review that says "The restaurant is expensive but the food is really fantastic", for example, the general SA evaluates the overall sentiment towards the 'restaurant' as 'positive', while ABSA identifies the restaurant's aspect 'price' as 'negative' and 'food' aspect as 'positive'. Thus, ABSA enables a more specific and effective marketing strategy. In order to perform ABSA, it is necessary to identify what are the aspect terms or aspect categories included in the text, and judge the sentiments towards them. Accordingly, there exist four main areas in ABSA; aspect term extraction, aspect category detection, Aspect Term Sentiment Classification (ATSC), and Aspect Category Sentiment Classification (ACSC). It is usually conducted by extracting aspect terms and then performing ATSC to analyze sentiments for the given aspect terms, or by extracting aspect categories and then performing ACSC to analyze sentiments for the given aspect category. Here, an aspect category is expressed in one or more aspect terms, or indirectly inferred by other words. In the preceding example sentence, 'price' and 'food' are both aspect categories, and the aspect category 'food' is expressed by the aspect term 'food' included in the review. If the review sentence includes 'pasta', 'steak', or 'grilled chicken special', these can all be aspect terms for the aspect category 'food'. As such, an aspect category referred to by one or more specific aspect terms is called an explicit aspect. On the other hand, the aspect category like 'price', which does not have any specific aspect terms but can be indirectly guessed with an emotional word 'expensive,' is called an implicit aspect. So far, the 'aspect category' has been used to avoid confusion about 'aspect term'. From now on, we will consider 'aspect category' and 'aspect' as the same concept and use the word 'aspect' more for convenience. And one thing to note is that ATSC analyzes the sentiment towards given aspect terms, so it deals only with explicit aspects, and ACSC treats not only explicit aspects but also implicit aspects. This study seeks to find answers to the following issues ignored in the previous studies when applying the BERT pre-trained language model to ACSC and derives superior ACSC models. First, is it more effective to reflect the output vector of tokens for aspect categories than to use only the final output vector of [CLS] token as a classification vector? Second, is there any performance difference between QA (Question Answering) and NLI (Natural Language Inference) types in the sentence-pair configuration of input data? Third, is there any performance difference according to the order of sentence including aspect category in the QA or NLI type sentence-pair configuration of input data? To achieve these research objectives, we implemented 12 ACSC models and conducted experiments on 4 English benchmark datasets. As a result, ACSC models that provide performance beyond the existing studies without expanding the training dataset were derived. In addition, it was found that it is more effective to reflect the output vector of the aspect category token than to use only the output vector for the [CLS] token as a classification vector. It was also found that QA type input generally provides better performance than NLI, and the order of the sentence with the aspect category in QA type is irrelevant with performance. There may be some differences depending on the characteristics of the dataset, but when using NLI type sentence-pair input, placing the sentence containing the aspect category second seems to provide better performance. The new methodology for designing the ACSC model used in this study could be similarly applied to other studies such as ATSC.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.43-61
• /
• 2019

Development of technologies in artificial intelligence has been rapidly increasing with the Fourth Industrial Revolution, and researches related to AI have been actively conducted in a variety of fields such as autonomous vehicles, natural language processing, and robotics. These researches have been focused on solving cognitive problems such as learning and problem solving related to human intelligence from the 1950s. The field of artificial intelligence has achieved more technological advance than ever, due to recent interest in technology and research on various algorithms. The knowledge-based system is a sub-domain of artificial intelligence, and it aims to enable artificial intelligence agents to make decisions by using machine-readable and processible knowledge constructed from complex and informal human knowledge and rules in various fields. A knowledge base is used to optimize information collection, organization, and retrieval, and recently it is used with statistical artificial intelligence such as machine learning. Recently, the purpose of the knowledge base is to express, publish, and share knowledge on the web by describing and connecting web resources such as pages and data. These knowledge bases are used for intelligent processing in various fields of artificial intelligence such as question answering system of the smart speaker. However, building a useful knowledge base is a time-consuming task and still requires a lot of effort of the experts. In recent years, many kinds of research and technologies of knowledge based artificial intelligence use DBpedia that is one of the biggest knowledge base aiming to extract structured content from the various information of Wikipedia. DBpedia contains various information extracted from Wikipedia such as a title, categories, and links, but the most useful knowledge is from infobox of Wikipedia that presents a summary of some unifying aspect created by users. These knowledge are created by the mapping rule between infobox structures and DBpedia ontology schema defined in DBpedia Extraction Framework. In this way, DBpedia can expect high reliability in terms of accuracy of knowledge by using the method of generating knowledge from semi-structured infobox data created by users. However, since only about 50% of all wiki pages contain infobox in Korean Wikipedia, DBpedia has limitations in term of knowledge scalability. This paper proposes a method to extract knowledge from text documents according to the ontology schema using machine learning. In order to demonstrate the appropriateness of this method, we explain a knowledge extraction model according to the DBpedia ontology schema by learning Wikipedia infoboxes. Our knowledge extraction model consists of three steps, document classification as ontology classes, proper sentence classification to extract triples, and value selection and transformation into RDF triple structure. The structure of Wikipedia infobox are defined as infobox templates that provide standardized information across related articles, and DBpedia ontology schema can be mapped these infobox templates. Based on these mapping relations, we classify the input document according to infobox categories which means ontology classes. After determining the classification of the input document, we classify the appropriate sentence according to attributes belonging to the classification. Finally, we extract knowledge from sentences that are classified as appropriate, and we convert knowledge into a form of triples. In order to train models, we generated training data set from Wikipedia dump using a method to add BIO tags to sentences, so we trained about 200 classes and about 2,500 relations for extracting knowledge. Furthermore, we evaluated comparative experiments of CRF and Bi-LSTM-CRF for the knowledge extraction process. Through this proposed process, it is possible to utilize structured knowledge by extracting knowledge according to the ontology schema from text documents. In addition, this methodology can significantly reduce the effort of the experts to construct instances according to the ontology schema.

• Journal of KIISE:Software and Applications
• /
• v.33 no.2
• /
• pp.243-251
• /
• 2006

In multi-document summarization by means of salient sentence extraction, it is important to remove redundant information. In the removal process, the similarities and differences of sentences are considered. In this paper, we propose a method for multi-document summarization which extracts salient sentences without having redundant sentences by way of cohesive term clustering method that utilizes co-occurrence Information. In the cohesive term clustering method, we assume that each term does not exist independently, but rather it is related to each other in meanings. To find the relations between terms, we cluster sentences according to topics and use the co-occurrence information oi terms in the same topic. We conduct experimental tests with the DUC(Document Understanding Conferences) data. In the tests, our method shows better performance of summarization than other summarization methods which use term co-occurrence information based on term cohesion of document or sentence unit, and simple statistical information.

• Korean Journal of Oriental Medicine
• /
• v.17 no.3
• /
• pp.97-104
• /
• 2011

Objectives : In this paper, we proposed a method for selecting reliable variables from various vocal features such as frequency derivative features, frequency band ratios, intensities of 5 vowels and an intensity of a sentence, since some features are sensitive to the variation of a subject's utterance. Methods : To obtain the reliable voice variables, the coefficient of variation (CV) was used as the index to evaluate the level of reliability. Since the distributions of a few features are not Gaussian, but are instead skewed to the right or left, we transformed the features by taking the log or square root. Moreover, the definition of the variables that are suitable to represent the vocal property was explained and analyzed. Results : At first, we recorded the vowels and the sentence five times both in the morning and afternoon of the same day, totally ten recordings from each of six subjects (three males and three females). We then analyzed the CVs of each subject's voice to obtain the stable features with a sufficient repeatability. The features having less than 20% CVs for all six subjects were selected. As a result, 92 stable variables from the 222 features were extracted, which included all the transformed variables. Conclusions : Voice can be widely used to classify the four constitution types and to recognize one's health condition from extracting meaningful features as physical quantity in traditional Korean medicine or Western medicine. Therefore, stable voice variables can be useful in the u-Healthcare system of personalized medicine and for improving diagnostic accuracy.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.1
• /
• pp.24-29
• /
• 2022

Semantic role labeling task used in various natural language processing fields, such as information extraction and question answering systems, is the task of identifying the arugments for a given sentence and predicate. Predicate used as semantic role labeling input are extracted using lexical analysis results such as POS-tagging, but the problem is that predicate can't extract all linguistic patterns because predicate in korean language has various patterns, depending on the meaning of sentence. In this paper, we propose a korean predicate recognition method using neural network model with pre-trained embedding models and lexical features. The experiments compare the performance on the hyper parameters of models and with or without the use of embedding models and lexical features. As a result, we confirm that the performance of the proposed neural network model was 92.63%.