An Error-based Investigation of Statistical and Neural Machine Translation Performance on Hindi-to-Tamil and English-to-Tamil

Akshai Ramesh, Venkatesh Balavadhani Parthasa, Rejwanul Haque, Andy Way


Abstract
Statistical machine translation (SMT) was the state-of-the-art in machine translation (MT) research for more than two decades, but has since been superseded by neural MT (NMT). Despite producing state-of-the-art results in many translation tasks, neural models underperform in resource-poor scenarios. Despite some success, none of the present-day benchmarks that have tried to overcome this problem can be regarded as a universal solution to the problem of translation of many low-resource languages. In this work, we investigate the performance of phrase-based SMT (PB-SMT) and NMT on two rarely-tested low-resource language-pairs, English-to-Tamil and Hindi-to-Tamil, taking a specialised data domain (software localisation) into consideration. This paper demonstrates our findings including the identification of several issues of the current neural approaches to low-resource domain-specific text translation.
Anthology ID:
2020.wat-1.22
Volume:
Proceedings of the 7th Workshop on Asian Translation
Month:
December
Year:
2020
Address:
Suzhou, China
Venue:
WAT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
178–188
Language:
URL:
https://aclanthology.org/2020.wat-1.22
DOI:
Bibkey:
Cite (ACL):
Akshai Ramesh, Venkatesh Balavadhani Parthasa, Rejwanul Haque, and Andy Way. 2020. An Error-based Investigation of Statistical and Neural Machine Translation Performance on Hindi-to-Tamil and English-to-Tamil. In Proceedings of the 7th Workshop on Asian Translation, pages 178–188, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
An Error-based Investigation of Statistical and Neural Machine Translation Performance on Hindi-to-Tamil and English-to-Tamil (Ramesh et al., WAT 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.wat-1.22.pdf