• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.4
• /
• pp.138-147
• /
• 2007

Metabolic pathway is a series of chemical reactions occuning within a cell and can be used for drug development and understanding of life phenomenon. Many biologists are trying to extract metabolic pathway information from huge literatures for their metabolic-circuit regulation study. We propose a text-mining technique based on the keyword and pattern. Proposed technique utilizes a web robot to collect huge papers and stores them into a local database. We use gene ontology to increase compound recognition rate and NCBI Tokenizer library to recognize useful information without compound destruction. Furthermore, we obtain useful sentence patterns representing metabolic pathway from papers and KEGG database. We have extracted 66 patterns in 20,000 documents for Glycosphingolipid species from KEGG, a representative metabolic database. We verify our system for nineteen compounds in Glycosphingolipid species. The result shows that the recall is 95.1%, the precision 96.3%, and the processing time 15 seconds. Proposed text mining system is expected to be used for metabolic pathway reconstruction.

• The KIPS Transactions:PartA
• /
• v.15A no.2
• /
• pp.125-134
• /
• 2008

We implemented a system being able to suggest example sentences for multiple choice tests, considering the level of students. To build the system, we designed an automatic method for sentence generation, which made it possible to control the difficulty degree of questions. For the proper evaluation in the multiple choice tests, proper size of question pools is required. To satisfy this requirement, a system which can generate various and numerous questions and their example sentences in a fast way should be used. In this paper, we designed an automatic generation method using a linguistic resource called WordNet. For the automatic generation, firstly, we extracted keywords from the existing sentences with the morphological analysis and candidate terms with similar meaning to the keywords in Korean WordNet space are suggested. When suggesting candidate terms, we transformed the existing Korean WordNet scheme into a new scheme to construct the concept similarity matrix. The similarity degree between concepts can be ranged from 0, representing synonyms relationships, to 9, representing non-connected relationships. By using the degree, we can control the difficulty degree of newly generated questions. We used two methods for evaluating semantic similarity between two concepts. The first one is considering only the distance between two concepts and the second one additionally considers positions of two concepts in the Korean Wordnet space. With these methods, we can build a system which can help the instructors generate new questions and their example sentences with various contents and difficulty degree from existing sentences more easily.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.11
• /
• pp.555-562
• /
• 2016

Semantic Role Labeling (SRL) is to determine the semantic relation of a predicate and its argu-ments in a sentence. But Korean semantic role labeling has faced on difficulty due to its different language structure compared to English, which makes it very hard to use appropriate approaches developed so far. That means that methods proposed so far could not show a satisfied perfor-mance, compared to English and Chinese. To complement these problems, we focus on suffix information analysis, such as josa (case suffix) and eomi (verbal ending) analysis. Korean lan-guage is one of the agglutinative languages, such as Japanese, which have well defined suffix structure in their words. The agglutinative languages could have free word order due to its de-veloped suffix structure. Also arguments with a single morpheme are then labeled with statistics. In addition, machine learning algorithms such as Support Vector Machine (SVM) and Condi-tional Random Fields (CRF) are used to model SRL problem on arguments that are not labeled at the suffix analysis phase. The proposed method is intended to reduce the range of argument instances to which machine learning approaches should be applied, resulting in uncertain and inaccurate role labeling. In experiments, we use 15,224 arguments and we are able to obtain approximately 83.24% f1-score, increased about 4.85% points compared to the state-of-the-art Korean SRL research.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.1
• /
• pp.35-42
• /
• 2013

Developing English-Korean machine translation system requires the construction of information about the languages, and the amount of information in English-Korean transfer dictionary is especially critical to the translation quality. Newly created words are out-of-vocabulary words and they appear as they are in the translated sentence, which decreases the translation quality. Also, compound nouns make lexical and syntactic analysis complex and it is difficult to accurately translate compound nouns due to the lack of information in the transfer dictionary. In order to improve the translation quality of English-Korean machine translation, we must continuously expand the information of the English-Korean transfer dictionary by collecting the out-of-vocabulary words and the compound nouns frequently used. This paper proposes a method for expanding of the transfer dictionary, which consists of constructing corpus from internet newspapers, extracting the words which are not in the existing dictionary and the frequently used compound nouns, attaching meaning to the extracted words, and integrating with the transfer dictionary. We also develop the tool supporting the expansion of the transfer dictionary. The expansion of the dictionary information is critical to improving the machine translation system but requires much human efforts. The developed tool can be useful for continuously expanding the transfer dictionary, and so it is expected to contribute to enhancing the translation quality.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.2
• /
• pp.79-88
• /
• 2019

Machine translation (MT) system, especially Korean-Mongolian MT system, has recently attracted much attention due to its necessary for the globalization generation. Korean and Mongolian have the same sentence structure SOV and the arbitrarily changing of their words order does not change the meaning of sentences due to postpositional particles. The particles that are attached behind words to indicate their grammatical relationship to the clause or make them more specific in meaning. Hence, the particles play an important role in the translation between Korean and Mongolian. However, one Korean particle can be translated into several Mongolian particles. This is a major issue of the Korean-Mongolian MT systems. In this paper, to address this issue, we propose a method to use the combination of UTagger and a Korean-Mongolian particles table. UTagger is a system that can analyze morphologies, tag POS, and disambiguate homographs for Korean texts. The Korean-Mongolian particles table was manually constructed for matching Korean particles with those of Mongolian. The experiment on the test set extracted from the National Institute of Korean Language's Korean-Mongolian Learner's Dictionary shows that our method achieved the accuracy of 88.38% and it improved the result of using only UTagger by 41.48%.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.1
• /
• pp.1-8
• /
• 2021

In the political field of news articles, there are polarized and biased characteristics such as conservative and liberal, which is called political bias. We constructed keyword-based dataset to classify bias of news articles. Most embedding researches represent a sentence with sequence of morphemes. In our work, we expect that the number of unknown tokens will be reduced if the sentences are constituted by subwords that are segmented by the language model. We propose a document embedding model with subword tokenization and apply this model to SVM and feedforward neural network structure to classify the political bias. As a result of comparing the performance of the document embedding model with morphological analysis, the document embedding model with subwords showed the highest accuracy at 78.22%. It was confirmed that the number of unknown tokens was reduced by subword tokenization. Using the best performance embedding model in our bias classification task, we extract the keywords based on politicians. The bias of keywords was verified by the average similarity with the vector of politicians from each political tendency.

• Journal of Internet Computing and Services
• /
• v.22 no.6
• /
• pp.141-150
• /
• 2021

Based on Artificial Intelligence technology, AI-enabled warfare is expected to become the main issue in the future warfare. Natural language processing technology is a core technology of AI technology, and it can significantly contribute to reducing the information burden of underrstanidng reports, information objects and intelligences written in natural language by commanders and staff. In this paper, we propose a Language model-based Multi-source Information Integration (LAMII) framework to reduce the information overload of commanders and support rapid decision-making. The proposed LAMII framework consists of the key steps of representation learning based on language models in self-supervsied way and document integration using autoencoders. In the first step, representation learning that can identify the similar relationship between two heterogeneous sentences is performed using the self-supervised learning technique. In the second step, using the learned model, documents that implies similar contents or topics from multiple sources are found and integrated. At this time, the autoencoder is used to measure the information redundancy of the sentences in order to remove the duplicate sentences. In order to prove the superiority of this paper, we conducted comparison experiments using the language models and the benchmark sets used to evaluate their performance. As a result of the experiment, it was demonstrated that the proposed LAMII framework can effectively predict the similar relationship between heterogeneous sentence compared to other language models.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.8
• /
• pp.315-324
• /
• 2022

In this paper, we propose KoEPT, a Transformer-based generative model for automatic math word problems solving. A math word problem written in human language which describes everyday situations in a mathematical form. Math word problem solving requires an artificial intelligence model to understand the implied logic within the problem. Therefore, it is being studied variously across the world to improve the language understanding ability of artificial intelligence. In the case of the Korean language, studies so far have mainly attempted to solve problems by classifying them into templates, but there is a limitation in that these techniques are difficult to apply to datasets with high classification difficulty. To solve this problem, this paper used the KoEPT model which uses 'expression' tokens and pointer networks. To measure the performance of this model, the classification difficulty scores of IL, CC, and ALG514, which are existing Korean mathematical sentence problem datasets, were measured, and then the performance of KoEPT was evaluated using 5-fold cross-validation. For the Korean datasets used for evaluation, KoEPT obtained the state-of-the-art(SOTA) performance with 99.1% in CC, which is comparable to the existing SOTA performance, and 89.3% and 80.5% in IL and ALG514, respectively. In addition, as a result of evaluation, KoEPT showed a relatively improved performance for datasets with high classification difficulty. Through an ablation study, we uncovered that the use of the 'expression' tokens and pointer networks contributed to KoEPT's state of being less affected by classification difficulty while obtaining good performance.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.9
• /
• pp.381-386
• /
• 2023

Many existing test case generation researchers extract test cases from models. However, research on generating test cases from natural language requirements is required in practice. For this purpose, the combination of natural language analysis and requirements engineering is very necessary. However, Requirements analysis written in Korean is difficult due to the diverse meaning of sentence expressions. We research test case generation through natural language requirement definition analysis, C3Tree model, cause-effect graph, and decision table steps as one of the test case generation methods from Korean natural requirements. As an intermediate step, this paper generates test cases from C3Tree model-based decision tables using meta-modeling. This method has the advantage of being able to easily maintain the model-to-model and model-to-text transformation processes by modifying only the transformation rules. If an existing model is modified or a new model is added, only the model transformation rules can be maintained without changing the program algorithm. As a result of the evaluation, all combinations for the decision table were automatically generated as test cases.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.371-380
• /
• 2023

Relation extraction is to extract relationships between named entities from text. Traditionally, relation extraction methods only extract relations between predetermined subject and object entities. However, in end-to-end relation extraction, all possible relations must be extracted by considering the positions of the subject and object for each pair of entities, and so this method uses time and resources inefficiently. To alleviate this problem, this paper proposes a method that sets directions based on the positions of the subject and object, and extracts relations according to the directions. The proposed method utilizes existing relation extraction data to generate direction labels indicating the direction in which the subject points to the object in the sentence, adds entity position tokens and entity type to sentences to predict the directions using a pre-trained language model (KLUE-RoBERTa-base, RoBERTa-base), and generates representations of subject and object entities through probabilistic crossover operation. Then, we make use of these representations to extract relations. Experimental results show that the proposed model performs about 3 ~ 4%p better than a method for predicting integrated labels. In addition, when learning Korean and English data using the proposed model, the performance was 1.7%p higher in English than in Korean due to the number of data and language disorder and the values of the parameters that produce the best performance were different. By excluding the number of directional cases, the proposed model can reduce the waste of resources in end-to-end relation extraction.