Automatic Creation of a Sentence Aligned Sinhala-Tamil Parallel Corpus

Riyafa Abdul Hameed, Nadeeshani Pathirennehelage, Anusha Ihalapathirana, Maryam Ziyad Mohamed, Surangika Ranathunga, Sanath Jayasena, Gihan Dias, Sandareka Fernando


Abstract
A sentence aligned parallel corpus is an important prerequisite in statistical machine translation. However, manual creation of such a parallel corpus is time consuming, and requires experts fluent in both languages. Automatic creation of a sentence aligned parallel corpus using parallel text is the solution to this problem. In this paper, we present the first ever empirical evaluation carried out to identify the best method to automatically create a sentence aligned Sinhala-Tamil parallel corpus. Annual reports from Sri Lankan government institutions were used as the parallel text for aligning. Despite both Sinhala and Tamil being under-resourced languages, we were able to achieve an F-score value of 0.791 using a hybrid approach that makes use of a bilingual dictionary.
Anthology ID:
W16-3713
Volume:
Proceedings of the 6th Workshop on South and Southeast Asian Natural Language Processing (WSSANLP2016)
Month:
December
Year:
2016
Address:
Osaka, Japan
Venues:
WS | WSSANLP
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
124–132
Language:
URL:
https://aclanthology.org/W16-3713
DOI:
Bibkey:
Cite (ACL):
Riyafa Abdul Hameed, Nadeeshani Pathirennehelage, Anusha Ihalapathirana, Maryam Ziyad Mohamed, Surangika Ranathunga, Sanath Jayasena, Gihan Dias, and Sandareka Fernando. 2016. Automatic Creation of a Sentence Aligned Sinhala-Tamil Parallel Corpus. In Proceedings of the 6th Workshop on South and Southeast Asian Natural Language Processing (WSSANLP2016), pages 124–132, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Automatic Creation of a Sentence Aligned Sinhala-Tamil Parallel Corpus (Abdul Hameed et al., 2016)
Copy Citation:
PDF:
https://aclanthology.org/W16-3713.pdf