A Functional NLP System for Twi (Akan) Using Limited Data

David Sasu; Dennis Asamoah Owusu

A Functional NLP System for Twi (Akan) Using Limited Data

David Sasu
, Dennis Asamoah Owusu

NLPnorth

University of Maryland

Research output: Journal Article or Conference Article in Journal › Conference article › Research › peer-review

Abstract

Natural Language Processing (NLP) continues to advance. How- ever, native Ghanaian languages like many other languages in the world remain untouched. Limited availability of annotated data in these languages is, perhaps, the primary limiting factor. This work explores the development of a useful and practical NLP system for Twi, a native Ghanaian language, under the constraint of limited data. The result is a system developed using only 4.65 minutes of annotated speech data that allows searching for selected Twi songs by saying the song title in Twi.

Original language	English
Journal	ACM SIGCAS Conference on Computing and Sustainable Societies
Number of pages	2
ISSN	4503-9999
Publication status	Published - 2019

Keywords

Natural Language Processing
Machine Learning

Cite this

@inproceedings{27a834924428468a9c05bc328938a8d0,

title = "A Functional NLP System for Twi (Akan) Using Limited Data",

abstract = "Natural Language Processing (NLP) continues to advance. How- ever, native Ghanaian languages like many other languages in the world remain untouched. Limited availability of annotated data in these languages is, perhaps, the primary limiting factor. This work explores the development of a useful and practical NLP system for Twi, a native Ghanaian language, under the constraint of limited data. The result is a system developed using only 4.65 minutes of annotated speech data that allows searching for selected Twi songs by saying the song title in Twi.",

keywords = "Natural Language Processing, Machine Learning, Natural Language Processing, Machine Learning",

author = "David Sasu and \{Asamoah Owusu\}, Dennis",

note = "2/5-23: godkendt af DS uden OA da publikation er fra 2019 og ikke l{\ae}ngere t{\ae}ller i OA opg{\o}relse",

year = "2019",

language = "English",

journal = "ACM SIGCAS Conference on Computing and Sustainable Societies",

issn = "4503-9999",

}

TY - GEN

T1 - A Functional NLP System for Twi (Akan) Using Limited Data

AU - Sasu, David

AU - Asamoah Owusu, Dennis

N1 - 2/5-23: godkendt af DS uden OA da publikation er fra 2019 og ikke længere tæller i OA opgørelse

PY - 2019

Y1 - 2019

N2 - Natural Language Processing (NLP) continues to advance. How- ever, native Ghanaian languages like many other languages in the world remain untouched. Limited availability of annotated data in these languages is, perhaps, the primary limiting factor. This work explores the development of a useful and practical NLP system for Twi, a native Ghanaian language, under the constraint of limited data. The result is a system developed using only 4.65 minutes of annotated speech data that allows searching for selected Twi songs by saying the song title in Twi.

AB - Natural Language Processing (NLP) continues to advance. How- ever, native Ghanaian languages like many other languages in the world remain untouched. Limited availability of annotated data in these languages is, perhaps, the primary limiting factor. This work explores the development of a useful and practical NLP system for Twi, a native Ghanaian language, under the constraint of limited data. The result is a system developed using only 4.65 minutes of annotated speech data that allows searching for selected Twi songs by saying the song title in Twi.

KW - Natural Language Processing

KW - Machine Learning

KW - Natural Language Processing

KW - Machine Learning

M3 - Conference article

SN - 4503-9999

JO - ACM SIGCAS Conference on Computing and Sustainable Societies

JF - ACM SIGCAS Conference on Computing and Sustainable Societies

ER -

A Functional NLP System for Twi (Akan) Using Limited Data

Abstract

Keywords

Fingerprint

Cite this