TY - GEN
T1 - Neural vs Statistical Machine Translation
T2 - 2019 International Conference on Bangla Speech and Language Processing, ICBSLP 2019
AU - Hasan, Md Arid
AU - Alam, Firoj
AU - Chowdhury, Shammur Absar
AU - Khan, Naira
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/9
Y1 - 2019/9
N2 - Machine translation systems facilitate our communication and access to information, taking down language barriers. It is a well-researched area of Natural Language Processing (NLP), especially for resource-rich languages (e.g., language pairs in Europarl Parallel corpus). Besides these languages, there is also work on other language pairs including the Bangla-English language pair. In the current study, we aim to revisit both Statistical Machine Translation (SMT) and Neural Machine Translation (NMT) approaches using well-known, publicly available corpora for the Bangla-English (Bangla to English) language pair. We reported how the performance of the models differ based on the data and modeling techniques; consequently, we also compared the results obtained with Google's machine translation system. Our findings, across different corpora, indicates that NMT based approaches outperform SMT systems. Our results also outperform existing baselines by a large margin.
AB - Machine translation systems facilitate our communication and access to information, taking down language barriers. It is a well-researched area of Natural Language Processing (NLP), especially for resource-rich languages (e.g., language pairs in Europarl Parallel corpus). Besides these languages, there is also work on other language pairs including the Bangla-English language pair. In the current study, we aim to revisit both Statistical Machine Translation (SMT) and Neural Machine Translation (NMT) approaches using well-known, publicly available corpora for the Bangla-English (Bangla to English) language pair. We reported how the performance of the models differ based on the data and modeling techniques; consequently, we also compared the results obtained with Google's machine translation system. Our findings, across different corpora, indicates that NMT based approaches outperform SMT systems. Our results also outperform existing baselines by a large margin.
KW - Bangla-to-English
KW - Bidirectional LSTM
KW - Machine Translation
KW - Neural Machine Translation
KW - Statistical Machine Translation
UR - http://www.scopus.com/inward/record.url?scp=85085022332&partnerID=8YFLogxK
U2 - 10.1109/ICBSLP47725.2019.201502
DO - 10.1109/ICBSLP47725.2019.201502
M3 - Conference contribution
AN - SCOPUS:85085022332
T3 - 2019 International Conference on Bangla Speech and Language Processing, ICBSLP 2019
BT - 2019 International Conference on Bangla Speech and Language Processing, ICBSLP 2019
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 27 September 2019 through 28 September 2019
ER -