@inproceedings{kumar-etal-2021-iiit,
    title = "{IIIT} Hyderabad Submission To {WAT} 2021: Efficient Multilingual {NMT} systems for {I}ndian languages",
    author = "Kumar, Sourav  and
      Aggarwal, Salil  and
      Sharma, Dipti",
    editor = "Nakazawa, Toshiaki  and
      Nakayama, Hideki  and
      Goto, Isao  and
      Mino, Hideya  and
      Ding, Chenchen  and
      Dabre, Raj  and
      Kunchukuttan, Anoop  and
      Higashiyama, Shohei  and
      Manabe, Hiroshi  and
      Pa, Win Pa  and
      Parida, Shantipriya  and
      Bojar, Ond{\v{r}}ej  and
      Chu, Chenhui  and
      Eriguchi, Akiko  and
      Abe, Kaori  and
      Oda, Yusuke  and
      Sudoh, Katsuhito  and
      Kurohashi, Sadao  and
      Bhattacharyya, Pushpak",
    booktitle = "Proceedings of the 8th Workshop on Asian Translation (WAT2021)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2021.wat-1.25/",
    doi = "10.18653/v1/2021.wat-1.25",
    pages = "212--216",
    abstract = "This paper describes the work and the systems submitted by the IIIT-Hyderbad team in the WAT 2021 MultiIndicMT shared task. The task covers 10 major languages of the Indian subcontinent. For the scope of this task, we have built multilingual systems for 20 translation directions namely English-Indic (one-to- many) and Indic-English (many-to-one). Individually, Indian languages are resource poor which hampers translation quality but by leveraging multilingualism and abundant monolingual corpora, the translation quality can be substantially boosted. But the multilingual systems are highly complex in terms of time as well as computational resources. Therefore, we are training our systems by efficiently se- lecting data that will actually contribute to most of the learning process. Furthermore, we are also exploiting the language related- ness found in between Indian languages. All the comparisons were made using BLEU score and we found that our final multilingual sys- tem significantly outperforms the baselines by an average of 11.3 and 19.6 BLEU points for English-Indic (en-xx) and Indic-English (xx- en) directions, respectively."
}