{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T23:20:49Z","timestamp":1762039249413,"version":"build-2065373602"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T00:00:00Z","timestamp":1625443200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1007\/s10772-021-09865-5","type":"journal-article","created":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T09:02:55Z","timestamp":1625475775000},"page":"1047-1053","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Linguistically enhanced word segmentation for better neural machine translation of low resource agglutinative languages"],"prefix":"10.1007","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1343-8792","authenticated-orcid":false,"given":"Santwana","family":"Chimalamarri","sequence":"first","affiliation":[]},{"given":"Dinkar","family":"Sitaram","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,7,5]]},"reference":[{"key":"9865_CR1","doi-asserted-by":"crossref","unstructured":"Aharoni, R., & Goldberg, Y. (2017). Towards string-to-tree neural machine translation. arXiv preprint arXiv:1704.04743.","DOI":"10.18653\/v1\/P17-2021"},{"key":"9865_CR2","doi-asserted-by":"crossref","unstructured":"Alexandrescu, A., & Kirchhoff, K. (2006). Factored neural language models. In: Proceedings of the human language technology conference of the NAACL, Companion volume: short papers (pp. 1\u20134).","DOI":"10.3115\/1614049.1614050"},{"key":"9865_CR3","doi-asserted-by":"crossref","unstructured":"Ataman, D., & Federico, M. (2018). Compositional representation of morphologically-rich input for neural machine translation. arXiv preprint arXiv:1805.02036.","DOI":"10.18653\/v1\/P18-2049"},{"key":"9865_CR4","unstructured":"Bahdanau, D., Cho, K., & Bengio, Y. (2014). Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473."},{"key":"9865_CR5","first-page":"1137","volume":"3","author":"Y Bengio","year":"2003","unstructured":"Bengio, Y., Ducharme, R., Vincent, P., & Janvin, C. (2003). A neural probabilistic language model. The Journal of Machine Learning Research, 3, 1137\u20131155.","journal-title":"The Journal of Machine Learning Research"},{"key":"9865_CR6","doi-asserted-by":"crossref","unstructured":"Bostrom, K., & Durrett, G. (2020). Byte pair encoding is suboptimal for language model pretraining. arXiv preprint arXiv:2004.03720.","DOI":"10.18653\/v1\/2020.findings-emnlp.414"},{"key":"9865_CR7","doi-asserted-by":"crossref","unstructured":"Chen, H., Huang, S., Chiang, D., Dai, X., & Chen, J. (2018). Combining character and word information in neural machine translation using a multi-level attention. In: NAACL-HLT.","DOI":"10.18653\/v1\/N18-1116"},{"key":"9865_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3390298","volume":"19","author":"S Chimalamarri","year":"2020","unstructured":"Chimalamarri, S., Sitaram, D., & Jain, A. K. (2020). Morphological segmentation to improve crosslingual word embeddings for low resource languages. ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), 19, 1\u201315.","journal-title":"ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP)"},{"key":"9865_CR9","doi-asserted-by":"crossref","unstructured":"Cho, K., Van\u00a0Merri\u00ebnboer, B., Bahdanau, D., & Bengio, Y. (2014). On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259.","DOI":"10.3115\/v1\/W14-4012"},{"key":"9865_CR10","doi-asserted-by":"crossref","unstructured":"Dyer, C., Kuncoro, A., Ballesteros, M., & Smith, N. A. (2016). Recurrent neural network grammars. arXiv preprint arXiv:1602.07776.","DOI":"10.18653\/v1\/N16-1024"},{"key":"9865_CR11","doi-asserted-by":"crossref","unstructured":"Fadaei, H., & Faili, H.(2019). Using syntax for improving phrase-based smt in low-resource languages. Digital Scholarship in the Humanities.","DOI":"10.1093\/llc\/fqz033"},{"key":"9865_CR12","unstructured":"Garc\u00eda-Mart\u00ednez, M., Barrault, L., & Bougares, F. (2016). Factored neural machine translation architectures"},{"key":"9865_CR13","unstructured":"Haddow, B., & Kirefu, F. (2020). Pmindia\u2013A collection of parallel corpora of languages of India. arXiv preprint arXiv:2001.09907."},{"key":"9865_CR14","first-page":"7","volume":"2016","author":"CDV Hoang","year":"2016","unstructured":"Hoang, C. D. V., Haffari, R., & Cohn, T. (2016). Improving neural translation models with linguistic factors. Proceedings of the Australasian Language Technology Association Workshop, 2016, 7\u201314.","journal-title":"Proceedings of the Australasian Language Technology Association Workshop"},{"key":"9865_CR15","doi-asserted-by":"crossref","unstructured":"Klein, G., Kim, Y., Deng, Y., Senellart, J., & Rush, A. M. (2017). Opennmt: Open-source toolkit for neural machine translation. arXiv preprint arXiv:1701.02810.","DOI":"10.18653\/v1\/P17-4012"},{"key":"9865_CR16","unstructured":"Koehn, P., & Hoang, H. (2007). Factored translation models. In: Proceedings of the 2007 joint conference on empirical methods in natural language processing and computational natural language learning (EMNLP-CoNLL) (pp. 868\u2013876)."},{"key":"9865_CR17","doi-asserted-by":"crossref","unstructured":"Koehn, P., & Knowles, R. (2017). Six challenges for neural machine translation. arXiv preprint arXiv:1706.03872.","DOI":"10.18653\/v1\/W17-3204"},{"key":"9865_CR18","unstructured":"Kunchukuttan, A., Mishra, A., Chatterjee, R., Shah, R., & Bhattacharyya, P. (2014). Shata-anuvadak: Tackling multiway translation of Indian languages. In: LREC."},{"key":"9865_CR19","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1162\/tacl_a_00067","volume":"5","author":"J Lee","year":"2017","unstructured":"Lee, J., Cho, K., & Hofmann, T. (2017). Fully character-level neural machine translation without explicit segmentation. Transactions of the Association for Computational Linguistics, 5, 365\u2013378.","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"9865_CR20","doi-asserted-by":"crossref","unstructured":"Li, J., Xiong, D., Tu, Z., Zhu, M., Zhang, M., & Zhou, G. (2017). Modeling source syntax for neural machine translation. arXiv preprint arXiv:1705.01020.","DOI":"10.18653\/v1\/P17-1064"},{"key":"9865_CR21","unstructured":"Lin, C. Y. (2004). Rouge: A package for automatic evaluation of summaries. In: Text summarization branches out (pp. 74\u201381)."},{"key":"9865_CR22","unstructured":"Ling, W., Trancoso, I., Dyer, C., & Black, A. W. (2015). Character-based neural machine translation. ArXiv abs\/1511.04586."},{"key":"9865_CR23","doi-asserted-by":"crossref","unstructured":"Luong, M. T., & Manning, C. D. (2016). Achieving open vocabulary neural machine translation with hybrid word-character models. arXiv preprint arXiv:1604.00788.","DOI":"10.18653\/v1\/P16-1100"},{"key":"9865_CR24","doi-asserted-by":"crossref","unstructured":"Luong, M. T., Pham, H., & Manning, C. D. (2015). Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025.","DOI":"10.18653\/v1\/D15-1166"},{"key":"9865_CR25","doi-asserted-by":"crossref","unstructured":"Niehues, J., & Cho, E. (2017). Exploiting linguistic resources for neural machine translation using multi-task learning. arXiv preprint arXiv:1708.00993.","DOI":"10.18653\/v1\/W17-4708"},{"key":"9865_CR26","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., & Zhu, W. J. (2002). Bleu: A method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the Association for Computational Linguistics (pp. 311\u2013318).","DOI":"10.3115\/1073083.1073135"},{"key":"9865_CR27","unstructured":"Philip, J., Namboodiri, V. P., & Jawahar, C. (2019). A baseline neural machine translation system for Indian languages. arXiv preprint arXiv:1907.12437."},{"key":"9865_CR28","doi-asserted-by":"crossref","unstructured":"Popovi\u0107, M. (2017). chrf++: Words helping character n-grams. In: Proceedings of the second conference on machine translation (pp. 612\u2013618).","DOI":"10.18653\/v1\/W17-4770"},{"key":"9865_CR29","doi-asserted-by":"crossref","unstructured":"Provilkov, I., Emelianenko, D., & Voita, E. (2020). Bpe-dropout: Simple and effective subword regularization. ArXiv abs\/1910.13267.","DOI":"10.18653\/v1\/2020.acl-main.170"},{"key":"9865_CR30","unstructured":"Reddy, S., & Sharoff, S. (2011). Cross language pos taggers (and other tools) for Indian languages: An experiment with Kannada using telugu resources. In: Proceedings of the fifth international workshop on cross lingual information access (pp. 11\u201319)."},{"key":"9865_CR31","doi-asserted-by":"crossref","unstructured":"Schick, T., & Sch\u00fctze, H. (2019). Learning semantic representations for novel words: Leveraging both form and context. In: AAAI.","DOI":"10.1609\/aaai.v33i01.33016965"},{"key":"9865_CR32","doi-asserted-by":"crossref","unstructured":"Sennrich, R. (2016). How grammatical is character-level neural machine translation? Assessing mt quality with contrastive translation pairs. arXiv preprint arXiv:1612.04629.","DOI":"10.18653\/v1\/E17-2060"},{"key":"9865_CR33","doi-asserted-by":"crossref","unstructured":"Sennrich, R., & Haddow, B. (2016). Linguistic input features improve neural machine translation. arXiv preprint arXiv:1606.02892.","DOI":"10.18653\/v1\/W16-2209"},{"key":"9865_CR34","doi-asserted-by":"crossref","unstructured":"Sennrich, R., Haddow, B., & Birch, A. (2015). Neural machine translation of rare words with subword units. arXiv preprint arXiv:1508.07909.","DOI":"10.18653\/v1\/P16-1162"},{"key":"9865_CR35","unstructured":"Sutskever, I., Vinyals, O., & Le, Q. V. (2014). Sequence to sequence learning with neural networks. In: Advances in neural information processing systems (pp. 3104\u20133112)."},{"key":"9865_CR36","unstructured":"Virpioja, S., Smit, P., Gr\u00f6nroos, S. A., Kurimo, M., et\u00a0al. (2013). Morfessor 2.0: Python implementation and extensions for morfessor baseline."},{"key":"9865_CR37","unstructured":"Wu, Y., Schuster, M., Chen, Z., Le, Q. V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., Macherey, K., et\u00a0al. (2016). Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144."},{"key":"9865_CR38","doi-asserted-by":"crossref","unstructured":"Yuret, D., & Bi\u00e7ici, E. (2009). Modeling morphologically rich languages using split words and unstructured dependencies. In: Proceedings of the ACL-IJCNLP 2009 conference short papers (pp. 345\u2013348). Association for Computational Linguistics.","DOI":"10.3115\/1667583.1667690"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09865-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10772-021-09865-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-021-09865-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,18]],"date-time":"2021-11-18T10:21:19Z","timestamp":1637230879000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10772-021-09865-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,5]]},"references-count":38,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["9865"],"URL":"https:\/\/doi.org\/10.1007\/s10772-021-09865-5","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"type":"print","value":"1381-2416"},{"type":"electronic","value":"1572-8110"}],"subject":[],"published":{"date-parts":[[2021,7,5]]},"assertion":[{"value":"22 July 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}