DOI QR코드

DOI QR Code

Translation of Korean Object Case Markers to Mongolian's Suffixes

한국어 목적격조사의 몽골어 격 어미 번역

  • Received : 2018.10.05
  • Accepted : 2018.12.18
  • Published : 2019.02.28

Abstract

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%.

최근 기계 번역에 관한 연구들이 활발하게 이루어지고 있고 한국어와 몽골어 간의 상호 기계 번역 시스템도 개발되고 있다. 한국어와 몽골어는 계통적으로 같은 어족에 속하며 '주어+목적어+서술어'라는 비교적 자유로운 어순을 가지는 언어이고 어미와 조사가 발달한 것이 그 특징이다. 따라서 기계 번역 시 양언어의 조사나 어미의 의미를 잘 번역하는 것이 중요하다. 그러나 한국어 목적격 조사를 몽골어로 번역할 때 한국어 목적격 조사가 몽골어의 여러 격 어미로 번역이 될 수 있는데, 기존의 연구들은 한 가지 격 어미로만 번역해 정확한 의미를 전달하지 못하는 문제점이 있다. 본 논문에서는 이러한 문제점을 개선하기 위하여 한국어 형태소 분석과 동시에 품사 및 동형이의어 태깅 시스템인 유태거(UTagger)를 기반으로 하여 한국어 목적격 조사의 몽골어 격 어미 결정 방법을 제안한다. 제안하는 방법에서는 한국어 목적격 조사에 대응하는 몽골어 격 어미들을 살펴보고 데이터 테이블을 설계하여 적절한 격 어미를 결정한다. 제안한 방법의 성능을 검증하기 위하여 한국어기초사전에서 데이터를 추출하고 유태거와 비교 실험하였다. 실험 결과 목적격 조사를 바로 대격 어미로 번역한 유태거의 정확률은 46.9%인데 반해 본 논문에서 제안한 방법은 88.38%로 제안한 방법이 41.48%p 더 우수한 결과를 보였다.

Keywords

JBCRJM_2019_v8n2_79_f0001.png 이미지

Fig. 1. Output of the UTagger

JBCRJM_2019_v8n2_79_f0002.png 이미지

Fig. 2. Example of the Homograph Tagging

JBCRJM_2019_v8n2_79_f0003.png 이미지

Fig. 3. Learner's Dictionary of the Korean-Mongolian

JBCRJM_2019_v8n2_79_f0004.png 이미지

Fig. 5. Structure of the Table

JBCRJM_2019_v8n2_79_f0005.png 이미지

Fig. 6. Role of the Fields

JBCRJM_2019_v8n2_79_f0006.png 이미지

Fig. 7. Process of the Object Case Marker Decision

JBCRJM_2019_v8n2_79_f0007.png 이미지

Fig. 8. Final Output

JBCRJM_2019_v8n2_79_f0008.png 이미지

Fig. 4. (a) Translated Ratio of the Korean Object Case Markers to the Mongolian Object Case Markers, (b) Translated Ratio of the Korean Object Case Markers to the Other Mongolian Object Case Markers

Table 1. Multiple Mongolian Object Case Markers Corresponding to the Korean Object Case Markers

JBCRJM_2019_v8n2_79_t0001.png 이미지

Table 2. Translated Results of Object Case Markers on the Google

JBCRJM_2019_v8n2_79_t0002.png 이미지

Table 3. Result of the Examination

JBCRJM_2019_v8n2_79_t0003.png 이미지

Table 4. Data of the Examination

JBCRJM_2019_v8n2_79_t0004.png 이미지

Table 5. Various Meaning of the Verb '갈기다'

JBCRJM_2019_v8n2_79_t0005.png 이미지

Table 6. Type of the Error

JBCRJM_2019_v8n2_79_t0006.png 이미지

References

  1. L. Bates, "Korean Sentence Complexity Reduction for Machine Translation," Master's thesis, University of Seoul, 2017.
  2. W. K. Kim, "The Case information Processing and Korean-English Machine Translation," Korean Semantics, Vol.35, pp.23-43, Aug. 2011.
  3. C. S. Lim, H. A. Lee, M. S. Choi, B. G. Chang, K. J. Lee, and G. C. Kim, "English to Korean Machine Translation System based on Lexicalized Grammer," in Proceedings of Korea Information Science Society, Vol.24, No.2, pp.161-164, Oct. 1997.
  4. J. S. Kim, W. S. Kang, K. S. Choi, and G. C. Kim, "Design and Implementation of English Syntactic Analysis System for English-Korean Machine Translation," in Proceedings of Korea Information Science Society, Vol.16, No.2, pp.563-566, Oct. 1989.
  5. K. H. Moon, J. H. Lee, J. I. Kim, and G. J. Yang, "Resolution of Word Sense Ambiguities using Collocation Pattern in Japanese-to-Korean MT system," in Proceedings of Korea Information Science Society(B), Vol. 25, No. 8, pp. 1270-1280, Aug. 1998.
  6. B. Tsend Ayush, "Design of Korean and Mongolian sentence machine translation system," Master's thesis, Kangwon National University, 2012.
  7. Y. M. Kim, "Mongolian-Korean language Machine Translation System," Korea Multimedia Society International Conference, pp.50-52, Jul. 2011.
  8. T. Gantur, "Rule-based Machine Translation from Korean Verb to Mongolian Verb," Master's thesis, Soongsil University, 2010.
  9. A. Enkhsaruul, C. G. Song, and Y.-S. Kim, "A comparison between Korean and Mongolian eomi and josa for Korean to Mongolian machine translation system," in Proceedings of the Korean Association of Information Science and Technology Conference, pp.228-232, Oct. 2007.
  10. J. Ch. Shin and C. Ock, "A Korean Morphological Analyzer using a Pre-analyzed Partial Word-phrase Dictionary," Journal of KIISE:Software and Application, Vol.39, No.5, pp.415-424, May 2012.
  11. M. Altantsetseg, "A Comparative Study on the Case Markers between Korean and Mongolian languages: On Objective case and Adverbial case markers," Master's thesis, Kangwon National University, 2016.
  12. E. Khulan, "A comparison between Korean objective proposition and Mongolian," Journal of Korean Culture, Vol.12, pp.105-134, 2009.
  13. U. Bolor Erdene, "Error Analysis and Teaching Method of Case Markers 'eul/leul' for Mongolian Learners of Korean," New Language Education, Vol.102, pp.273-304, 2015.
  14. L. Buyandelger, "A Study on Lexical and Grammatical Errors of Mongolian Learners of Korean," Master's thesis, Keimyung University, Jun. 2015.
  15. B. Munkhtsetseg, "A Comparative study of Korean Case Marker and Mongolian Case Ending," Master's thesis, Chungbuk National University, 2013.
  16. S. J. Nam, "A Study about the interlanguage appeared on the Mongolian Korean Language Learners : Focused on the Case Particle," Master's thesis, Keimyung University, 2010.