Towards Producing Human-Validated Translation Resources for the Fula language through WordNet Linking

Khalil Mrini, Martin Benjamin


Abstract
We propose methods to link automatically parsed linguistic data to the WordNet. We apply these methods on a trilingual dictionary in Fula, English and French. Dictionary entry parsing is used to collect the linguistic data. Then we connect it to the Open Multilingual WordNet (OMW) through two attempts, and use confidence scores to quantify accuracy. We obtained 11,000 entries in parsing and linked about 58% to the OMW on the first attempt, and an additional 14% in the second one. These links are due to be validated by Fula speakers before being added to the Kamusi Project’s database.
Anthology ID:
W17-7908
Volume:
Proceedings of the Workshop Human-Informed Translation and Interpreting Technology
Month:
September
Year:
2017
Address:
Varna, Bulgaria
Editors:
Irina Temnikova, Constantin Orasan, Gloria Corpas Pastor, Stephan Vogel
Venue:
RANLP
SIG:
Publisher:
Association for Computational Linguistics, Shoumen, Bulgaria
Note:
Pages:
58–64
Language:
URL:
https://doi.org/10.26615/978-954-452-042-7_008
DOI:
10.26615/978-954-452-042-7_008
Bibkey:
Cite (ACL):
Khalil Mrini and Martin Benjamin. 2017. Towards Producing Human-Validated Translation Resources for the Fula language through WordNet Linking. In Proceedings of the Workshop Human-Informed Translation and Interpreting Technology, pages 58–64, Varna, Bulgaria. Association for Computational Linguistics, Shoumen, Bulgaria.
Cite (Informal):
Towards Producing Human-Validated Translation Resources for the Fula language through WordNet Linking (Mrini & Benjamin, RANLP 2017)
Copy Citation:
PDF:
https://doi.org/10.26615/978-954-452-042-7_008