Abstract
This work presents an in-depth analysis of machine translations of morphologically-rich Indo-Aryan and Dravidian languages under zero-resource conditions. It focuses on Zero-Shot Systems for these languages and leverages transfer-learning by exploiting target-side monolingual corpora and parallel translations from other languages. These systems are compared with direct translations using the BLEU and TER metrics. Further, Zero-Shot Systems are used as pre-trained models for fine-tuning with real human-generated data taken in different proportions that range from 100 sentences to the entire training set. Performances of the Indo-Aryan and Dravidian languages are compared with a focus on their morphological complexity. The systems with a Dravidian source language performed much better and reached very near to the level of direct translations. This is observed likely due to morphological richness and complexity in the language, which in turn provided more room for transfer-learning in this case. A comparative analysis based on language families has been done. These systems were fine-tuned further, which in turn outperformed direct translations with just 500 parallel sentences for a Dravidian source language. However, systems with an Indo-Aryan source language showed similar performance after getting fine-tuned with 10,000 sentences.
- Ruchit Agrawal, Mihir Shekhar, and Dipti Misra. 2017. Integrating knowledge encoded by linguistic phenomena of indian languages with neural machine translation. In Proceedings of the International Conference on Mining Intelligence and Knowledge Exploration. Springer, 287--296.Google Scholar
Cross Ref
- Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In Proceedings of the 3rd International Conference on Learning Representations (ICLR'15), San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, 2015.Google Scholar
- Yonatan Belinkov, Nadir Durrani, Fahim Dalvi, Hassan Sajjad, and James Glass. 2017. What do neural machine translation models learn about morphology?. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, 861--872. DOI:https://doi.org/10.18653/v1/P17-1080Google Scholar
Cross Ref
- Christian Bentz, Tatyana Ruzsics, Alexander Koplenig, and Tanja Samardzic. 2016. A comparison between morphological complexity measures: Typological data vs. language corpora. In Proceedings of the Workshop on Computational Linguistics for Linguistic Complexity (cl4lc’16). 142--153.Google Scholar
- Himanshu Choudhary, Aditya Kumar Pathak, Rajiv Ratan Saha, and Ponnurangam Kumaraguru. 2018. Neural machine translation for english-tamil. In Proceedings of the 3rd Conference on Machine Translation: Shared Task Papers. 770--775.Google Scholar
Cross Ref
- Jonathan H. Clark, Chris Dyer, Alon Lavie, and Noah A. Smith. 2011. Better hypothesis testing for statistical machine translation: Controlling for optimizer instability. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: Short Papers--Volume 2. Association for Computational Linguistics, 176--181.Google Scholar
- Fahim Dalvi, Nadir Durrani, Hassan Sajjad, Yonatan Belinkov, and Stephan Vogel. 2017. Understanding and improving morphological learning in the neural machine translation decoder. In Proceedings of the 8th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Asian Federation of Natural Language Processing, Taipei, Taiwan, 142--151.Google Scholar
- Sandipan Dandapat and Christian Federmann. 2018. Iterative data augmentation for neural machine translation: A low resource case study for english-telugu. In Proceedings of the 21st Annual Conference of the European Association for Machine Translation. European Association for Machine Translation, 287--292.Google Scholar
- Thanh-Le Ha, Jan Niehues, and Alexander Waibel. 2016. Toward multilingual neural machine translation with universal encoder and decoder. Arxiv Preprint Arxiv:1611.04798 (2016).Google Scholar
- Girish Nath Jha. 2012. The TDIL program and the Indian language corpora initiative. In Proceedings of the Language Resources and Evaluation Conference.Google Scholar
- Melvin Johnson, Mike Schuster, Quoc V. Le, Maxim Krikun, Yonghui Wu, Zhifeng Chen, Nikhil Thorat, Fernanda Viégas, Martin Wattenberg, Greg Corrado, et al. 2017. Google’s multilingual neural machine translation system: Enabling zero-shot translation. Trans. Assoc. Comput. Ling. 5 (2017), 339--351.Google Scholar
Cross Ref
- Kimmo Kettunen. 2014. Can type-token ratio be used to show morphological complexity of languages? J. Quant. Ling. 21, 3 (2014), 223--245.Google Scholar
Cross Ref
- Philipp Koehn. 2005. Europarl: A parallel corpus for statistical machine translation. In Proceedings of the MT Summit, Vol. 5. Citeseer, 79--86.Google Scholar
- Anoop Kunchukuttan and Pushpak Bhattacharyya. 2017. Learning variable length units for SMT between related languages via byte pair encoding. In Proceedings of the 1st Workshop on Subword and Character Level Models in NLP. 14--24.Google Scholar
Cross Ref
- Anoop Kunchukuttan, Abhijit Mishra, Rajen Chatterjee, Ritesh Shah, and Pushpak Bhattacharyya. 2014. Shata-anuvadak: Tackling multiway translation of indian languages. In Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC’14).Google Scholar
- Surafel Melaku Lakew, Mauro Cettolo, and Marcello Federico. 2018. A comparison of transformer and recurrent neural networks on multilingual neural machine translation. In Proceedings of the 27th International Conference on Computational Linguistics. 641--652.Google Scholar
- Surafel M. Lakew, Quintino F. Lotito, Matteo Negri, Marco Turchi, and Marcello Federico. 2017. Improving zero-shot translation of low-resource languages. In Proceedings of the 14th International Workshop on Spoken Language Translation.Google Scholar
- Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. BLEU: A method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics. Association for Computational Linguistics, 311--318.Google Scholar
- Alberto Poncelas, Dimitar Shterionov, Andy Way, Gideon Maillette de Buy Wenniger, and Peyman Passban. 2018. Investigating backtranslation in neural machine translation. In Proceedings of the 21st Annual Conference of the European Association for Machine Translation. European Association for Machine Translation, 249--258.Google Scholar
- Martin Popel and Ondřej Bojar. 2018. Training tips for the transformer model. Prague Bull. Math. Ling. 110, 1 (2018), 43--70.Google Scholar
Cross Ref
- Matīss Rikters, Mārcis Pinnis, and Rihards Krišlauks. 2018. Training and adapting multilingual NMT for less-resourced and morphologically rich languages. In Proceedings of the 11th International Conference on Language Resources and Evaluation (LREC’18).Google Scholar
- Sukanta Sen, Kamal Kumar Gupta, Asif Ekbal, and Pushpak Bhattacharyya. 2018. IITP-MT at WAT2018: Transformer-based multilingual indic-english neural machine translation system. In Proceedings of the 5th Workshop on Asian Translation (WAT’18).Google Scholar
- Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016. Improving neural machine translation models with monolingual data. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Vol. 1. 86--96.Google Scholar
Cross Ref
- Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016. Neural machine translation of rare words with subword units. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Vol. 1. 1715--1725.Google Scholar
Cross Ref
- Lierni Sestorain, Massimiliano Ciaramita, Christian Buck, and Thomas Hofmann. 2018. Zero-shot dual machine translation. Arxiv Preprint Arxiv:1805.10338 (2018).Google Scholar
- Ivan Skorokhodov, Anton Rykachevskiy, Dmitry Emelyanenko, Sergey Slotin, and Anton Ponkratov. 2018. Semi-supervised neural machine translation with language models. In Proceedings of the AMTA 2018 Workshop on Technologies for MT of Low Resource Languages (LoResMT’18). 37--44.Google Scholar
- Matthew Snover, Bonnie Dorr, Richard Schwartz, Linnea Micciulla, and John Makhoul. 2006. A study of translation edit rate with targeted human annotation. In Proceedings of Association for Machine Translation in the Americas (Vol. 200, No. 6).Google Scholar
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998--6008.Google Scholar
- Zhen Yang, Wei Chen, Feng Wang, and Bo Xu. 2018. Improving neural machine translation with conditional sequence generative adversarial nets. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), Vol. 1. 1346--1355.Google Scholar
Cross Ref
Index Terms
Translating Morphologically Rich Indian Languages under Zero-Resource Conditions
Recommendations
Discourse Tagging for Indian Languages
CICLing 2014: Proceedings of the 15th International Conference on Computational Linguistics and Intelligent Text Processing - Volume 8403Indian Language Discourse Project is to develop large corpus annotated with various types of discourse relations which are explicit and implicit. As an initial step towards it we have annotated corpus in three languages, Hindi, Tamil and Malayalam ...
Translating from morphologically complex languages: a paraphrase-based approach
HLT '11: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1We propose a novel approach to translating from a morphologically complex language. Unlike previous research, which has targeted word inflections and concatenations, we focus on the pairwise relationship between morphologically related words, which we ...
Stemming resource-poor Indian languages
Stemming is a basic method for morphological normalization of natural language texts. In this study, we focus on the problem of stemming several resource-poor languages from Eastern India, viz., Assamese, Bengali, Bishnupriya Manipuri and Bodo. While ...






Comments