|
Advanced search
Previous page
|
Title
Evaluation of a Runyankore grammar engine for healthcare messages |
Full text
http://pubs.cs.uct.ac.za/id/eprint/1236/1/EvalRunyanINLG17.pdf |
Date
2017 |
Author(s)
Byamugisha, Ms Joan; Keet, Dr. C. Maria; DeRenzi, Dr. Brian |
Abstract
Natural Language Generation (NLG) can be used to generate personalized health information, which is especially useful when provided in one's own language. However, the NLG technique widely used in different domains and languages---templates---was shown to be inapplicable to Bantu languages, due to their characteristic agglutinative structure. We present here our use of the grammar engine NLG technique to generate text in Runyankore, a Bantu language indigenous to Uganda. Our grammar engine adds to previous work in this field with new rules for cardinality constraints, prepositions in roles, the passive, and phonological conditioning. We evaluated the generated text with linguists and non-linguists, who regarded most text as grammatically correct and understandable; and over 60\% of them regarded all the text generated by our system to have been authored by a human being. |
Subject(s)
Artificial intelligence |
Language
en |
Publisher
ALC |
Relation
http://pubs.cs.uct.ac.za/id/eprint/1236/ |
Type of publication
Conference paper |
Format
application/pdf |
Identifier
Byamugisha, Ms Joan and Keet, Dr. C. Maria and DeRenzi, Dr. Brian (2017) Evaluation of a Runyankore grammar engine for healthcare messages, Proceedings of 10th International Natural Language Generation conference (INLG'17), 4-7 Sept 2017, Santiago de Compostela, Spain, 105-113, Department of Computer Science, University of Cape Town, ALC. |
Repository
Cape Town - CS Research Documents, University of Cape Town
|
Added to C-A: 2020-03-05;08:11:21 |
© Connecting-Africa 2004-2024 | Last update: Friday, March 8, 2024 |
Webmaster
|