Comparing Statistical and Neural Machine Translation Performance on Hindi-To-Tamil and English-To-Tamil

Abstract

Phrase-based statistical machine translation (PB-SMT) has been the dominant paradigm in machine translation (MT) research for more than two decades. Deep neural MT models have been producing state-of-the-art performance across many translation tasks for four to five years. To put it another way, neural MT (NMT) took the place of PB-SMT a few years back and currently represents the state-of-the-art in MT research. Translation to or from under-resourced languages has been historically seen as a challenging task. Despite producing state-of-the-art results in many translation tasks, NMT still poses many problems such as performing poorly for many low-resource language pairs mainly because of its learning task’s data-demanding nature. MT researchers have been trying to address this problem via various techniques, e.g., exploiting source- and/or target-side monolingual data for training, augmenting bilingual training data, and transfer learning. Despite some success, none of the present-day benchmarks have entirely overcome the problem of translation in low-resource scenarios for many languages. In this work, we investigate the performance of PB-SMT and NMT on two rarely tested under-resourced language pairs, English-to-Tamil and Hindi-to-Tamil, taking a specialised data domain into consideration. This paper demonstrates our findings and presents results showing the rankings of our MT systems produced via a social media-based human evaluation scheme.

Statistical machine translation for Indic languages

“…In the year 2021, translation of EN and HI-to-TA languages using both SMT and NMT has been presented by Ramesh et al (2020). The disadvantages of NMT have been shown in their experiments such as the occurrence of numerous errors by NMT when interpreting domain terms and OOV phrases.…”

NLP-reliant Neural Machine Translation techniques used in smart city applications

“…Philip [13] provides and analyses an automated framework to obtain such a corpus for Indian. Ramesh et al [14] demonstrates MT systems produced via a social media-based human evaluation scheme. Singh and Kumar [15] inspected on the word vectors of 66 ambiguous Punjabi nouns for an explicit WSD system of Punjabi language.…”

Google Translate Performance in Translating English Passive Voice into Indonesian

“…Hence, this study provides an opportunity for future researchers to expand further research on the performance of Google Translate over time, for instance; seeing the accuracy level of passive voice translation conducted by Google Translate or by testing using other types of sentences. It is deemed essential to test Google Translate's accuracy in translating English passive voice into Indonesian using accuracy evaluation methods such as manual or automatic evaluation (e.g., BLEU (Bilingual Evaluation Understudy) scores (Aiken, 2019;Ramesh et al, 2021), CompareMT (Neubig et al, 2019), MTComparEval, Memsource criteria (see www.memsource.com), translation closeness metric, and etc. ).…”

“…In late 2016, Google Translate then adopted Neural Machine Translation (NMT) which is called as Google Neural Machine Translation (GNMT). Compared with SMT, GNMT is capable of fixing translation difficulties and threats by providing a more fluent and legible translation by handling morphology and syntax five times better than SMT systems (Ramesh et al, 2021). Thus, GNMT translations were claimed to be more precise and fluent compared to translations of SMT systems.…”