Machine Translation of English Language to Mizo Language

Abstract

The communication between different regional languages is always inevitable fact which requires a lot of effort to make meaningful in terms of technology. The machine translation methods have been endeavoured to fill this impediment. The Neural Machine Translation is one of the efforts which recently gained a remarkable enhancement in the matter of human judgement over the conventional approaches like phrasebased machine translation and statistical machine translation. Thus, the advances of neural machine translation approach influence the challenge in the mind of people. The different types of online translation and mobile application tools such as Google Translate, DeepL, SYSTRAN, etc. applications were came up to tackle this issue. But such kinds of convenience translation tools are not available for English-Mizo parallel languages. In this paper, we have tried to enhance the ability of language translation by owing the supremacy capability of Neural Machine Translation to improve the English to Mizo conversion in BiLingual Evaluation Understudy metric.

Building Machine Translation Systems for the Next Thousand Languages

“…Our 2020), the numerous results on the largely South-and Central American languages from the first AmericasNLP conference (Mager et al, 2021), and the Inuktitut language of Canada (Joanis et al, 2020). Datasets for lower-resourced languages of India have also sprung up, including the 13-language PMIndia , and datasets focused on languages of the Northeast like Mizo (Thihlum et al, 2020), Khasi (Laskar et al, 2021) and Assamese (Laskar et al, 2020). Finally, a variety of such datasets and models are available for public use on HuggingFace 10 or Zenodo 11 .…”

An empirical study on English-Mizo Statistical Machine Translation with Bible Corpus

“…The author reported that the MT system prediction is reasonable based on fluency but worse on accuracy. [7] conducted a study to evaluate the English to Mizo NMT system on several test datasets from different domains. [26] conducted a study on English to Mizo MT systems (SMT and NMT) on a training dataset collected from various online sources.…”

“…Mizo is a Kuki-chin language, a branch of the Sino-Tibetan language, and belongs to the Tibeto-Burman family. The word order in English and Mizo is different; English follows SVO (Subject-Verb-Object), and Mizo follows OSV (Object-Subject-Verb); however, Mizo sometimes follows SVO like English [7]. Furthermore, the second person pronoun "you" is used in English to represent both the singular and plural, whereas the Mizo language has unique phrases for this (for singular "I" and plural "in").…”

“…Prefixes and suffixes are affixes related to language morphology. Some of the Mizo language prefixes include "in, " "ti, " and "inti", and depending on the sentence, "ti" is occasionally adjusted and used as "tih" [7]. When suffixes are added after the stem word in Mizo, they can affect the part of speech, similar to how suffixes in English can change a verb into a noun.…”

Experiences of Adapting Multimodal Machine Translation Techniques for Hindi

“…A similar method was used for English-Hindi [41], and this method was able to generate better results compared to UNMT. A comparison of results was performed on the Mizo VisualGenome dataset [31] with Transformer, BiLSTM, and PBSMT models [35,57,68], where the transformer outperforms the other models. However, it was observed that NMT-based models generate a poor-quality translation for longer sentences.…”