• Annual Conference on Human and Language Technology
• /
• 2012.10a
• /
• pp.113-116
• /
• 2012

UTagger는 한국어 의미 처리를 위해 개발된 형태소분석기이며 의미 분열 기능도 가지고 있다. 정확률이 매우 높고 다앙한 기능을 갖추고 있으나 이전에 개발된 다른 형태소 분석기에 비하여 속도가 느리다는 단점을 가지고 있었다. 형태소 분석기의 빠른 속도는 많은 분야에서 요구되고 있기 때문에 본 논문에서는 UTagger의 정확률을 유지하면서 속도를 향상시키는 캐시(Cache) 방법과, 정확률을 조금 낮추면서 향상시키는 다앙한 방법들을 제시한다. 또한 상황에 따라 적합한 방법을 선택할 때 참조가 되도록 하기 위해 각 방법들 실험 결과를 정리한다.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.184-189
• /
• 2017

With the advent of robust deep learning method, Neural machine translation has recently become a dominant paradigm and achieved adequate results in translation between popular languages such as English, German, and Spanish. However, its results in under-resourced languages Korean and Vietnamese are still limited. This paper reports an attempt at constructing a bidirectional Korean-Vietnamese Neural machine translation system with the supporting of Korean analysis tool - UTagger, which includes morphological analyzing, POS tagging, and WSD. Experiment results demonstrate that UTagger can significantly improve translation quality of Korean-Vietnamese NMT system in both translation direction. Particularly, it improves approximately 15 BLEU scores for the translation from Korean to Vietnamese direction and 3.12 BLEU scores for the reverse direction.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.184-189
• /
• 2017

With the advent of robust deep learning method, Neural machine translation has recently become a dominant paradigm and achieved adequate results in translation between popular languages such as English, German, and Spanish. However, its results in under-resourced languages Korean and Vietnamese are still limited. This paper reports an attempt at constructing a bidirectional Korean-Vietnamese Neural machine translation system with the supporting of Korean analysis tool - UTagger, which includes morphological analyzing, POS tagging, and WSD. Experiment results demonstrate that UTagger can significantly improve translation quality of Korean-Vietnamese NMT system in both translation direction. Particularly, it improves approximately 15 BLEU scores for the translation from Korean to Vietnamese direction and 3.12 BLEU scores for the reverse direction.

• 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%.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.504-509
• /
• 2018

Neural machine translation (NMT) has recently achieved the state-of-the-art performance. However, it is reported failing in the word sense disambiguation (WSD) for several popular language pairs. In this paper, we explore the extent to which NMT systems are able to disambiguate the Korean homographs. Homographs, words with different meanings but the same written form, cause the word choice problems for NMT systems. Consistent with the popular language pairs, we discover that NMT systems fail to translate Korean homographs correctly. We provide a Korean word sense disambiguation tool-UTagger to use for improvement of NMT's translation quality. We conducted translation experiments using Korean-English and Korean-Vietnamese language pairs. The experimental results show that UTagger can significantly improve the translation quality of NMT in terms of the BLEU, TER, and DLRATIO evaluation metrics.

• Language and Information
• /
• v.18 no.2
• /
• pp.169-199
• /
• 2014

This study was performed to assume the Sematic role of the obligatory argument of the predicate in a Korean sentence, and to accomplish the task to attach the assumed thematic role to the real corpus. With this study, the maximum of the Sematic role was determined and the Criterion of the Sematic role was set. The maximum of the Sematic role was determined 22. This study arranged the Sematic role of case marker and attached the Sematic role to the predicate of the sentence within The standard Korean Dictionary. The program to attach the thematic role was developed(UTagger-SR). The Sematic role of case marker and Case frame dictionary was equipped in this program. By attaching the Sematic role, it was found that the most important the Sematic role in the korean sentence is the theme of the predicate and the next is the subject of the predicate.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.587-590
• /
• 2018

한국어 목적격 조사를 몽골어 격 어미로 번역할 때 한국어 목적격 조사가 몽골어의 여러 격 어미로 번역이 될 수 있는데, 기존의 연구들은 한가지 격 어미로만 번역해 정확한 의미를 전달하지 못하는 문제점이 있다. 이런 문제점을 개선하기 위하여 본 논문에서는 한국어 형태소 분석과 동시에 품사 및 동형이의어 태깅 시스템인 유태거(UTagger)를 기반으로 한국어 목적격 조사의 몽골어 격 어미 결정 방법을 제안한다. 제안한 방법의 성능을 검증하기 위하여 한국어기초사전에서 데이터를 추출하고 유태거와 비교 실험하였다. 실험 결과 유태거의 정확률은 72%인데 반해 제안한 방법은 94%로 제안한 방법이 22%p 더 우수한 결과를 보였다.

• Annual Conference on Human and Language Technology
• /
• 2014.10a
• /
• pp.251-254
• /
• 2014

의미역 결정은 문장의 서술어와 그 서술어에 속하는 논항들 사이의 의미관계를 결정하는 문제로, 기계학습에 의한 의미역을 부착하기 위해서는 의미역 부착 말뭉치를 필요로 한다. 본 논문에서 격틀 사전을 사용하여 각 서술어의 논항의 의미역을 제한하여 작업자가 빠르게 의미역 말뭉치를 구축할 수 있도록 하는 의미역 반자동 부착 도구(UTagger-SR)를 개발하였다.

• The Journal of the Korea Contents Association
• /
• v.19 no.2
• /
• pp.11-21
• /
• 2019

It has been about 20 years since the English subject was formally taught in public elementary schools in Korea. The present research aims to analyze the studies regarding 'primary English' implemented in Korea during the time period. I have investigated 6,467 theses or research papers in total that were published in Korea with the help of the corpus programs Utagger and WordSmith Tools. The results show that for the last 20 years the number of overall studies appears to have increased since the year 1997, although the recent trend seems to be in recession. The research scope ranges from 'teaching-learning interaction' to 'curriculum' and 'assessment', which have been steadily investigated for 20 years. Furthermore, researchers sometimes appear to have followed the English education policy by conducting particular investigations like 'immersion program' or 'native English speaking teachers' in a certain time period. Recently, researchers started to have interest in the cutting-edge ICT. In conclusion, the academic field of 'primary English' in Korea has grown in quantity, and the spectrum of research areas has been expanded for the past 20 years. It is hoped that the results of this research will help set a new direction for future research.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.205-210
• /
• 2020

한국어 자연어처리 분야가 발달하면서 동형이의어 분별을 한 단계 넘어선 다의어 분별의 중요성이 점점 상승하고 있다. 최근에 다의어가 태깅된 "모두의 말뭉치"가 발표되었고, 이 말뭉치는 다의어가 태깅된 최초의 공개 말뭉치로써 다의어 연구가 본격적으로 진행될 수 있음을 의미한다. 본 논문에서는 이 말뭉치를 학습하여 작동하는 다의어 분별의 초기 모델을 제시하며, 이 모델의 실험 결과는 차후 연구를 위한 비교 기준점이 될 수 있다. 이 모델은 딥러닝을 사용하지 않은 통계형으로 개발되었고, 형태소분석과 동형이의어 분별은 기존의 UTagger로 해결하고 말뭉치 자원 외에도 UWordMap을 사용하여 다의어 분별을 보조하였다. 이 모델의 정확률은 약 87%이며, 다의어 분별 전에 형태소분석 또는 동형이의어 분별 단계에서 오류가 난 것을 포함한다. 현재까지 공개된 이 말뭉치는 오직 명사만 다의어 주석이 있기 때문에 명사만 정확률 측정 대상이 되었다. 이 연구를 통하여 다의어 분별의 어려움과, 다의어 분별에는 동형이의어 분별과는 다른 방법이 필요하다는 것을 확인할 수 있었다.