Transferred Embeddings for Igbo Similarity, Analogy, and Diacritic Restoration Tasks.

Ezeani, Ignatius and Onyenwe, Ikechukwu E. and Hepple, Mark (2018) Transferred Embeddings for Igbo Similarity, Analogy, and Diacritic Restoration Tasks. In: COLING 2018 - 3rd Workshop on Semantic Deep Learning, SemDeep 2018 - Proceedings. COLING 2018 - 3rd Workshop on Semantic Deep Learning, SemDeep 2018 - Proceedings . UNSPECIFIED, pp. 30-38. ISBN 9781948087568

Full text not available from this repository.

Abstract

Existing NLP models are mostly trained with data from well-resourced languages. Most minority languages face the challenge of lack of resources - data and technologies - for NLP research. Building these resources from scratch for each minority language will be very expensive, time-consuming and amount largely to unnecessarily re-inventing the wheel. In this paper, we applied transfer learning techniques to create Igbo word embeddings from a variety of existing English trained embeddings. Transfer learning methods were also used to build standard datasets for Igbo word similarity and analogy tasks for intrinsic evaluation of embeddings. These projected embeddings were also applied to diacritic restoration task. Our results indicate that the projected models not only outperform the trained ones on the semantic-based tasks of analogy, word-similarity, and odd-word identifying, but they also achieve enhanced performance on the diacritic restoration with learned diacritic embeddings.

Item Type:
Contribution in Book/Report/Proceedings
Additional Information:
DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.
ID Code:
183644
Deposited By:
Deposited On:
11 Jan 2023 17:05
Refereed?:
Yes
Published?:
Published
Last Modified:
11 Jan 2023 17:05