Abstract
We take up the task of large-scale evaluation of neural machine transliteration between English and Indic languages, with a focus on multilingual transliteration to utilize orthographic similarity between Indian languages. We create a corpus of 600K word pairs mined from parallel translation corpora and monolingual corpora, which is the largest transliteration corpora for Indian languages mined from public sources. We perform a detailed analysis of multilingual transliteration and propose an improved multilingual training recipe for Indic languages. We analyze various factors affecting transliteration quality like language family, transliteration direction and word origin.- Anthology ID:
- 2021.eacl-main.303
- Volume:
- Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
- Month:
- April
- Year:
- 2021
- Address:
- Online
- Editors:
- Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3469–3475
- Language:
- URL:
- https://aclanthology.org/2021.eacl-main.303
- DOI:
- 10.18653/v1/2021.eacl-main.303
- Cite (ACL):
- Anoop Kunchukuttan, Siddharth Jain, and Rahul Kejriwal. 2021. A Large-scale Evaluation of Neural Machine Transliteration for Indic Languages. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3469–3475, Online. Association for Computational Linguistics.
- Cite (Informal):
- A Large-scale Evaluation of Neural Machine Transliteration for Indic Languages (Kunchukuttan et al., EACL 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/2021.eacl-main.303.pdf
- Code
- anoopkunchukuttan/indic_transiteration_analysis
- Data
- Dakshina