한국융합학회논문지 (Journal of the Korea Convergence Society)

  • 제12권7호
  • /
  • Pages.37-44
  • /
  • 2021
  • /
  • 2233-4890(pISSN)
  • /
  • 2713-6353(eISSN)
한국융합학회 (Korea Convergence Society)
권호 표지
DOI QR코드

DOI QR Code

최신 기계번역 품질 예측 연구

Research on Recent Quality Estimation

  • 어수경 (고려대학교 컴퓨터학과) ;
  • 박찬준 (고려대학교 컴퓨터학과) ;
  • 문현석 (고려대학교 컴퓨터학과) ;
  • 서재형 (고려대학교 컴퓨터학과) ;
  • 임희석 (고려대학교 컴퓨터학과)
  • Eo, Sugyeong (Department of Computer Science and Engineering, Korea University) ;
  • Park, Chanjun (Department of Computer Science and Engineering, Korea University) ;
  • Moon, Hyeonseok (Department of Computer Science and Engineering, Korea University) ;
  • Seo, Jaehyung (Department of Computer Science and Engineering, Korea University) ;
  • Lim, Heuiseok (Department of Computer Science and Engineering, Korea University)
  • 투고 : 2021.04.07
  • 심사 : 2021.07.20
  • 발행 : 2021.07.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

기계번역 품질 예측(Quality Estimation, QE)은 정답 문장(Reference sentence) 없이도 기계번역 결과의 질을 평가할 수 있으며, 활용도가 높다는 점에서 그 필요성이 대두되고 있다. Conference on machine translation(WMT)에서 매년 이와 관련한 shared task가 열리고 있고 최근에는 대용량 데이터 기반 Pretrained language model(PLM)을 적용한 연구들이 주로 진행되고 있다. 본 논문에서는 기계번역 품질 예측 task에 대한 설명 및 연구 동향에 대한 전반적인 survey를 진행했고, 최근 자주 활용되는 PLM의 특징들에 대해 정리하였다. 더불어 아직 활용된 바가 없는 multilingual BART 모델을 이용하여 기존 연구들인 XLM, multilingual BERT, XLM-RoBERTa와 의 비교 실험 및 분석을 진행하였다. 실험 결과 어떤 사전 학습된 다중언어 모델이 QE에 적용했을 때 가장 효과적인지 확인하였을 뿐 아니라 multilingual BART 모델의 QE 태스크 적용 가능성을 확인했다.

Quality estimation (QE) can evaluate the quality of machine translation output even for those who do not know the target language, and its high utilization highlights the need for QE. QE shared task is held every year at Conference on Machine Translation (WMT), and recently, researches applying Pretrained Language Model (PLM) are mainly being conducted. In this paper, we conduct a survey on the QE task and research trends, and we summarize the features of PLM. In addition, we used a multilingual BART model that has not yet been utilized and performed comparative analysis with the existing studies such as XLM, multilingual BERT, and XLM-RoBERTa. As a result of the experiment, we confirmed which PLM was most effective when applied to QE, and saw the possibility of applying the multilingual BART model to the QE task.

키워드

과제정보

This research was supported by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program(IITP-2020-2018-0-01405) supervised by the IITP(Institute for Information & Communications Technology Planning & Evaluation) and this research was supported by the MSIT(Ministry of Science and ICT), Korea, under the ICT Creative Consilience program(IITP-2021-0-01819) supervised by the IITP(Institute for Information & communications Technology Planning & Evaluation)

참고문헌

  1. L. Specia, F. Blain, V. Logacheva, R. Astudillo & A. Martins. (2018). Findings of the wmt 2018 shared task on quality estimation. Association for Computational Linguistics. DOI : 10.18653/v1/W18-6451
  2. E. Fonseca, L. Yankovskaya, A. F. Martins, M. Fishel & C. Federmann. (2019). Findings of the WMT 2019 shared tasks on quality estimation. In Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2), 1-10. DOI : 10.18653/v1/W19-5401
  3. L. Specia, K. Shah, J. G. De Souza & T. Cohn (2013). QuEst-A translation quality estimation framework. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics: System Demonstrations, 79-84.
  4. L. Specia, C. Scarton & G. H. Paetzold (2018). Quality estimation for machine translation. Synthesis Lectures on Human Language Technologies, 11(1), 1-162. DOI : 10.2200/S00854ED1V01Y201805HLT039
  5. L. Specia, D. Raj & M. Turchi (2010). Machine translation evaluation versus quality estimation. Machine translation, 24(1), 39-50. DOI : 10.1007/s10590-010-9077-2
  6. D. Lee. (2020). Two-phase cross-lingual language model fine-tuning for machine translation quality estimation. In Proceedings of the Fifth Conference on Machine Translation. (pp. 1024-1028).
  7. Y. Baek, Z. M. Kim, J. Moon, H. Kim & E. Park. (2020). Patquest: Papago translation quality estimation. In Proceedings of the Fifth Conference on Machine Translation. (pp. 991-998).
  8. G. Lample & A. Conneau. (2019). Cross-lingual language model pretraining. arXiv preprint arXiv:1901.07291.
  9. J. Devlin, M. W. Chang, K. Lee & K. Toutanova. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805. DOI : 10.18653/v1/N19-1423
  10. A. Conneau et al. (2019). Unsupervised cross-lingual representation learning at scale. arXiv preprint arXiv:1911.02116. DOI : 10.18653/v1/P19-4007
  11. Y. Liu et al. (2020). Multilingual denoising pre-training for neural machine translation. Transactions of the Association for Computational Linguistics, 8, 726-742. https://doi.org/10.1162/tacl_a_00343
  12. E. Bicici. & A. Way. (2014). Referential translation machines for predicting translation quality. Association for Computational Linguistics. DOI : 10.18653/v1/w15-3035
  13. R. Soricut, N. Bach & Z. Wang. (2012). The SDL language weaver systems in the WMT12 quality estimation shared task. In Proceedings of the Seventh Workshop on Statistical Machine Translation. (pp. 145-151).
  14. N. Q. Luong, B. Lecouteux & L. Besacier. (2013). LIG system for WMT13 QE task: Investigating the usefulness of features in word confidence estimation for MT. In 8th Workshop on Statistical Machine Translation. (pp. 386-391).
  15. C. Hardmeier, J. Nivre & J. Tiedemann. (2012). Tree kernels for machine translation quality estimation. In Seventh Workshop on Statistical Machine Translation, Montreal, Canada, June 7-8, 2012. (pp. 109-113). Association for Computational Linguistics.
  16. R. N. Patel. (2016). Translation quality estimation using recurrent neural network. arXiv preprint arXiv:1610.04841. DOI : 10.18653/v1/W16-2389
  17. H. Kim & J. H. Lee. (2016). Recurrent neural network based translation quality estimation. In Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers. (pp. 787-792). DOI : 10.18653/v1/w16-2384
  18. K. Cho et al. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078. DOI : 10.3115/v1/d14-1179
  19. S. Hochreiter & J. Schmidhuber. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780. DOI : 10.1162/neco.1997.9.8.1735
  20. H. Kim, J. H. Lee & S. H. Na. (2017, September). Predictor-estimator using multilevel task learning with stack propagation for neural quality estimation. In Proceedings of the Second Conference on Machine Translation. (pp. 562-568). DOI : 10.18653/v1/w17-4763
  21. J. Wang, K. Fan, B. Li, F. Zhou, B. Chen, Y. Shi & L. Si. (2018). Alibaba submission for WMT18 quality estimation task. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers. (pp. 809-815). DOI : 10.18653/v1/w18-6465
  22. A. Vaswani et al. (2017). Attention is all you need. In Advances in neural information processing systems (pp. 5998-6008).
  23. F. Kepler et al. (2019). Unbabel's Participation in the WMT19 Translation Quality Estimation Shared Task. arXiv preprint arXiv:1907.10352. DOI : 10.18653/v1/W19-5406
  24. H. Kim, J. H. Lim, H. K. Kim & S. H. Na. (2019). QE BERT: bilingual BERT using multi-task learning for neural quality estimation. In Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2). (pp. 85-89). DOI : 10.18653/v1/W19-5407
  25. T. Ranasinghe, C. Orasan & R. Mitkov. (2020). TransQuest at WMT2020: Sentence-Level Direct Assessment. arXiv preprint arXiv:2010.05318.
  26. D. Lee. (2020). Two-phase cross-lingual language model fine-tuning for machine translation quality estimation. In Proceedings of the Fifth Conference on Machine Translation. (pp. 1024-1028).
  27. M. Wang et al. (2020, November). Hw-tsc's participation at wmt 2020 quality estimation shared task. In Proceedings of the Fifth Conference on Machine Translation. (pp. 1056-1061).
  28. H. Wu et al. (2020, November). Tencent submission for WMT20 Quality Estimation Shared Task. In Proceedings of the Fifth Conference on Machine Translation. (pp. 1062-1067).
  29. M. Snover, B. Dorr, R. Schwartz, L. Micciulla & J. Makhoul. (2006, August). A study of translation edit rate with targeted human annotation. In Proceedings of association for machine translation in the Americas (Vol. 200, No. 6).
  30. G. Wenzek et al. (2019). Ccnet: Extracting high quality monolingual datasets from web crawl data. arXiv preprint arXiv:1911.00359.
  31. T. Pires, E. Schlinger & D. Garrette. (2019). How multilingual is multilingual bert?. arXiv preprint arXiv:1906.01502. DOI : 10.18653/v1/p19-1493
  32. M. Lewis et al. (2019). Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461. DOI : 10.18653/v1/2020.acl-main.703
  33. T. Wolf et al. (2019). HuggingFace's Transformers: State-of-the-art natural language processing. arXiv preprint arXiv:1910.03771.
  34. C. Park & H. Lim. (2020). A Study on the Performance Improvement of Machine Translation Using Public Korean-English Parallel Corpus. Journal of Digital Convergence, 18(6), 271-277. https://doi.org/10.14400/JDC.2020.18.6.271
  35. C. Park, Y. Yang, K. Park & H. Lim. (2020). Decoding strategies for improving low-resource machine translation. Electronics, 9(10), 1562. https://doi.org/10.3390/electronics9101562