Improved Unsupervised Statistical Machine Translation via Unsupervised Word Sense Disambiguation for a Low-Resource and Indic Languages

REFERENCES

• S. Edunov, M. Ott, M. Auli, and D. Grangier, “Understanding back-translation at scale,” arXiv preprint arXiv:1808.09381, 2018.
   Google Scholar
• N. K. Jadoon, W. Anwar, U. I. Bajwa, and F. Ahmad, “Statistical machine translation of Indian languages: A survey,” Neural Comput. Appl., Vol. 31, no. 7, pp. 2455–2467, 2019. DOI: 10.1007/s00521-017-3206-2.
   Web of Science ®Google Scholar
• P. Koehn, Statistical Machine Translation. New York: Cambridge University Press, 2010.
   Google Scholar
• P. Koehn and R. Knowles, “Six challenges for neural machine translation,” arXiv preprint arXiv:1706.03872, 2017.
   Google Scholar
• A. Mikel, L. Gorka, and A. Eneko, “Unsupervised statistical machine translation,” Brussels; Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. arXiv, arXiv:1809.01272, 2018.
   Google Scholar
• A. Mikel, L. Gorka, and A. Eneko, “An effective approach to unsupervised machine translation,” arXiv preprint arXiv:1902.01313, 2019.
   Google Scholar
• G. Lample, M. Ott, A. Conneau, L. Denoyer, and M. A. Ranzato, “Phrase-based & neural unsupervised machine translation,” arXiv preprint arXiv:1804.07755, 2018.
   Google Scholar
• A. Tezcan, V. Hoste, and L. Macken, “Estimating word-level quality of statistical machine translation output using monolingual information alone,” Nat. Lang. Eng., Vol. 26, no. 1, pp. 73–94, 2020.
   Web of Science ®Google Scholar
• A. Kumar and V. Goyal, “Hindi to Punjabi machine translation system based on statistical approach,” J. Stat. Manage. Syst., Vol. 21, no. 4, pp. 547–552, 2018. DOI: 10.1080/09720510.2018.1466963.
   Web of Science ®Google Scholar
• R. K. Chakrawarti and P. Bansal, “Approaches for improving Hindi to English machine translation system,” Indian J. Sci. Technol., Vol. 10, no. 16, pp. 1–8, 2017. DOI: 10.17485/ijst/2017/v10i16/111895.
   Google Scholar
• N. K. Jadoon, W. Anwar, and N. Durrani, “Machine translation approaches and survey for Indian languages,” arXiv preprint arXiv:1701.04290, 2017.
   Google Scholar
• S. Mall and U. C. Jaiswal, “Survey: Machine translation for Indian language,” Int. J. Appl. Eng. Res., Vol. 13, no. 1, pp. 202–209, 2018.
   Google Scholar
• R. Ananthakrishnan, P. Bhattacharyya, M. Sasikumar, and R. M. Shah, “Some issues in automatic evaluation of English-Hindi MT: More blues for bleu,” ICON, 2007.
   Google Scholar
• R. N. Patel, P. B. Pimpale, and M. Sasikumar, “Machine translation in Indian languages: Challenges and resolution,” J. Intell. Syst., Vol. 28, no. 3, pp. 437–445, 2019.
   Web of Science ®Google Scholar
• R. Navigli, “Word sense disambiguation: A survey,” ACM Comput. Surv. (CSUR), Vol. 41, no. 2, pp. 1–69, 2009. DOI: 10.1145/1459352.1459355.
   Web of Science ®Google Scholar
• M. Bevilacqua, T. Pasini, A. Raganato, and R. Navigli, “Recent trends in word sense disambiguation: A survey,” in Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21, International Joint Conference on Artificial Intelligence, Inc, Vienna, pp. 4330–4338.
   Google Scholar
• M. Carpuat and D. Wu, “Evaluating the word sense disambiguation performance of statistical machine translation,” in Companion Volume to the Proceedings of Conference Including Posters/Demos and Tutorial Abstracts, 2005.
   Google Scholar
• M. Carpuat and D. Wu, “Improving statistical machine translation using word sense disambiguation,” in Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Prague, June 2007, pp. 61–72.
   Google Scholar
• M. Carpuat, Word Sense Disambiguation for Statistical Machine Translation. Hong Kong University of Science and Technology (Hong Kong), 2008.
   Google Scholar
• K. Papineni, S. Roukos, T. Ward, and W. J. Zhu, “Bleu: A method for automatic evaluation of machine translation,” in Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL), Philadelphia, July 2002, pp. 311–318.
   Google Scholar
• A. Agarwal and A. Lavie, “METEOR: An automatic metric for MT evaluation with improved correlation with human judgments,” in Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, Ann Arbor, June 2005, pp. 65–72.
   Google Scholar
• Q. Dou and K. Knight, “Large scale decipherment for out-of-domain machine translation,” in Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Jeju Island, Korea, 12–14 July 2012, pp. 266–275.
   Google Scholar
• Q. Dou and K. Knight, “Dependency-based decipherment for resource-limited machine translation,” in Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Seattle, Washington, USA, 18–21 October 2013, 1668–1676.
   Google Scholar
• Q. Dou, A. Vaswani, K. Knight, and C. Dyer, “Unifying Bayesian inference and vector space models for improved decipherment,” in Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, Beijing, China, July 26–31, 2015, pp. 836–845.
   Google Scholar
• S. Ravi and K. Knight, “Deciphering foreign language,” in Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics, Portland, Oregon, June 19–24, 2011, pp. 12–21.
   Google Scholar
• V. Siivola, T. Hirsimaki, and S. Virpioja, “On growing and pruning Kneser–Ney smoothed N-gram models,” IEEE Trans. Audio Speech Lang. Process., Vol. 15, no. 5, pp. 1617–1624, 2007.
   Google Scholar
• N. Ueffing, G. Haffari, and A. Sarkar, “Transductive learning for statistical machine translation,” in Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, Prague, Czech Republic, June 2007, pp. 25–32.
   Google Scholar
• P. Koehn and J. Schroeder, “Experiments in domain adaptation for statistical machine translation,” in Proceedings of the Second Workshop on Statistical Machine Translation, Prague, June 2007, pp. 224–227.
   Google Scholar
• Y. Lü, J. Huang, and Q. Liu, “Improving statistical machine translation performance by training data selection and optimization,” in Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Prague, June 2007, pp. 343–350.
   Google Scholar
• S. Matsoukas, A. V. Rosti, and B. Zhang, “Discriminative corpus weight estimation for machine translation,” in Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, Singapore, 6–7 August 2009, pp. 708–717.
   Google Scholar
• G. Foster, C. Goutte, and R. Kuhn, “Discriminative instance weighting for domain adaptation in statistical machine translation,” in Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, MIT, Massachusetts, USA, 9–11 October 2010, pp. 451–459.
   Google Scholar
• A. Vaswani, Y. Zhao, V. Fossum, and D. Chiang, “Decoding with large-scale neural language models improves translation,” in Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Seattle, Washington, USA, 18–21 October 2013, pp. 1387–1392.
   Google Scholar
• H. Sujaini, “Improving the role of language model in statistical machine translation (Indonesian-Javanese),” Int. J. Electr. Comput. Eng., Vol. 10, no. 2, pp. 2102–2109, 2020.
   Google Scholar
• C. Baziotis, B. Haddow, and A. Birch, “Language model prior for low-resource neural machine translation,” arXiv preprint arXiv, Vol. 2004, pp. 14928, 2020.
   Google Scholar
• K. Rottmann and S. Vogel, “Word reordering in statistical machine translation with a POS-based distortion model,” in Proceedings of the 11th Conference on Theoretical and Methodological Issues in Machine Translation of Natural Languages: Papers. Skövde, Sweden, 2007, pp. 171–180.
   Google Scholar
• E. Agirre and P. Edmonds, Word Sense Disambiguation: Algorithms and Applications. Vol. 33. Springer Science & Business Media, 2007
   Google Scholar
• Y. K. Lee and H. T. Ng, “An empirical evaluation of knowledge sources and learning algorithms for word sense disambiguation,” in Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), Philadelphia, July 2002, pp. 41–48.
   Google Scholar
• H. Y. Huang, Z. Yang, and P. Jian, “Unsupervised word sense disambiguation using neighborhood knowledge,” in Proceedings of the 25th Pacific Asia Conference on Language, Information and Computation, Singapore, PACLIC, pp. 333–342.
   Google Scholar
• T. Martín Wanton and R. Berlanga Llavori, “A clustering-based approach for unsupervised word sense disambiguation,” Proces. del Leng. Natural, Vol. 49, pp. 49–56, 2012.
   Google Scholar
• R. Giyanani, “A survey on word sense disambiguation,” IOSR J. Comput. Eng., Vol. 14, pp. 30–33, 2013. DOI: 10.9790/0661-1463033.
   Google Scholar
• N. Rahman and B. Borah, “An unsupervised method for word sense disambiguation,” J. King Saud Univ.-Comput. Inf.Sci., 2021. DOI: 10.1016/j.jksuci.2021.07.022.
   Web of Science ®Google Scholar
• A. R. Pal and D. Saha, “Word sense disambiguation in Bengali language using unsupervised methodology with modifications,” Sādhanā, Vol. 44, no. 7, pp. 1–13, 2019.
   Web of Science ®Google Scholar
• S. Chauhan, P. Daniel, S. Saxena, and A. Sharma, “Fully unsupervised machine translation using context-aware word translation and denoising autoencoder,” Appl. Artif. Intell., Vol. 36, no. 1, 2022. DOI: 10.1080/08839514.2022.2031817.
   Web of Science ®Google Scholar
• A. Mikel, L. Gorka, and A. Eneko. “A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings,” arXiv preprint arXiv:1805.06297, 2018.
   Google Scholar
• S. Saxena, S. Chauhan, and P. Daniel, “Analysis of unsupervised statistical machine translation using cross-lingual word embedding for English–Hindi,” in International Conference on Computational Techniques and Applications, Singapore: Springer, 2022, pp. 61–68.
   Google Scholar
• F. J. Och, C. Tillmann, and H. Ney, “Improved alignment models for statistical machine translation,” in 1999 Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora, USA, 1999.
   Google Scholar
• M. Pelevina, N. Arefyev, C. Biemann, and A. Panchenko, “Making sense of word embeddings,” arXiv preprint arXiv:1708.03390, 2017.
   Google Scholar
• F. J. Och, “Minimum error rate training in statistical machine translation,” in Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, Sapporo, Japan, Jul. 2003, pp. 160–167.
   Google Scholar
• R. Sennrich, B. Haddow, and A. Birch, “Improving neural machine translation models with monolingual data,” arXiv preprint arXiv:1511.06709, 2016.
   Google Scholar
• D. Kakwani, A. Kunchukuttan, S. Golla, N. C. Gokul, A. Bhattacharyya, M. M. Khapra, and P. Kumar, “Inlpsuite: Monolingual corpora, evaluation benchmarks and pre-trained multilingual language models for Indian languages,” in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings of the Association for Computational Linguistics: EMNLP 2020, November 16–20, 2020, pp. 4948–4961.
   Google Scholar
• S. Chauhan, S. Saxena, and P. Daniel, “Monolingual and parallel corpora for Kangri low resource language,” arXiv preprint arXiv:2103.11596, 2021.
   Google Scholar
• S. Chauhan, P. Daniel, and S. Saxena, “Analysis of neural machine translation KANGRI language by unsupervised and semi supervised methods,” IETE. J. Res., 2020. DOI: 10.1080/03772063.2021.2016506.
   Web of Science ®Google Scholar
• M. Post, C. Callison-Burch, and M. Osborne, “Constructing parallel corpora for six Indian languages via crowdsourcing,” in Proceedings of the 7th Workshop on Statistical Machine Translation, Montreal, Canada, June 7–8, 2012. pp. 401–409.
   Google Scholar
• P. Koehn, H. Hoang, A. Birch, C. Callison-Burch, M. Federico, N. Bertoldi, and E. Herbst, “Moses: Open source toolkit for statistical machine translation,” in Proceedings of the ACL 2007 Demo and Poster Sessions, Prague, June 2007, pp. 177–180.
   Google Scholar
• K. Heafield, “KenLM: Faster and smaller language model queries,” in Proceedings of the 6th Workshop on Statistical Machine Translation, Edinburgh, Scotland, UK, July 30–31, 2011, pp. 187–197.
   Google Scholar
• C. Tillmann. A Unigram Orientation Model for Statistical Machine Translation. IBM Thomas J. Watson Research Center, Yorktown Heights, NY, 2004.
   Google Scholar
• Sydney Richards, UMM CSci Senior Seminar Conference, Nov. 2017, Morris, MN. Available: https://umm-csci.github.io/senior-seminar/seminars/fall2017/richards.pdf.
   Google Scholar