An error-based investigation of statistical and neural machine translation performance on Hindi-to-Tamil and English-to-Tamil
Ramesh, Akshai, Parthasarathy, Venkatesh Balavadhani, Haque, RejwanulORCID: 0000-0003-1680-0099 and Way, AndyORCID: 0000-0001-5736-5930
(2020)
An error-based investigation of statistical and neural machine translation performance on Hindi-to-Tamil and English-to-Tamil.
In: 7th Workshop on Asian Translation (WAT2020), 4 Dec 2020, Suzhou, China (Online).
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(SMT) was the state-of-the-art in machine translation (MT) research for more than two decades, but has since been superseded by neural MT (NMT).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.
This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:
Science Foundation Ireland (SFI) Research Centres Programme (Grant No. 13/RC/2106), European Research Council, European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 713567, Science Foundation Ireland (SFI) under Grant Number 13/RC/2077
ID Code:
25203
Deposited On:
04 Dec 2020 14:24 by
Rejwanul Haque
. Last Modified 05 Dec 2023 15:23