A method for measuring verb similarity for two closely related languages with application to Zulu and Xhosa
There are limited computational resources for Nguni languages and when improving availability for one of the languages, bootstrapping from a related language’s resources may be a cost-saving approach. This requires the ability to quantify similarity between any two closely related languages so as to...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
South African Institute of Computer Scientists and Information Technologists
2019-12-01
|
| Series: | South African Computer Journal |
| Online Access: | https://sacj.cs.uct.ac.za/index.php/sacj/article/view/698 |
| _version_ | 1818311393123762176 |
|---|---|
| author | Zola Mahlaza Catharina Maria Keet |
| author_facet | Zola Mahlaza Catharina Maria Keet |
| author_sort | Zola Mahlaza |
| collection | DOAJ |
| description | There are limited computational resources for Nguni languages and when improving availability for one of the languages, bootstrapping from a related language’s resources may be a cost-saving approach. This requires the ability to quantify similarity between any two closely related languages so as to make informed decisions, of which it is unclear how to measure it. We devised a method for quantifying similarity by adapting four extant similar measures, and present a method of quantifying the ratio of verbs that would need phonological conditioning due to consecutive vowels. The verbs selected are those relevant for weather forecasts for Xhosa and Zulu and newly specified as computational grammar rules. The 52 Xhosa and 49 Zulu rules share 42 rules, supporting informal impressions of their similarity. The morphosyntactic similarity reached 59.5% overall on the adapted Driver-Kroeber metric, with past tense rules only at 99.5%. This similarity score is a result of the variation in terminals mainly for the prefix of the verb. |
| first_indexed | 2024-12-13T08:01:14Z |
| format | Article |
| id | doaj.art-2e2c9eef8b814ae6b200cb90a02558fb |
| institution | Directory Open Access Journal |
| issn | 1015-7999 2313-7835 |
| language | English |
| last_indexed | 2024-12-13T08:01:14Z |
| publishDate | 2019-12-01 |
| publisher | South African Institute of Computer Scientists and Information Technologists |
| record_format | Article |
| series | South African Computer Journal |
| spelling | doaj.art-2e2c9eef8b814ae6b200cb90a02558fb2022-12-21T23:54:26ZengSouth African Institute of Computer Scientists and Information TechnologistsSouth African Computer Journal1015-79992313-78352019-12-0131234–5634–5610.18489/sacj.v31i2.698698A method for measuring verb similarity for two closely related languages with application to Zulu and XhosaZola Mahlaza0Catharina Maria Keet1University of Cape TownUniversity of Cape TownThere are limited computational resources for Nguni languages and when improving availability for one of the languages, bootstrapping from a related language’s resources may be a cost-saving approach. This requires the ability to quantify similarity between any two closely related languages so as to make informed decisions, of which it is unclear how to measure it. We devised a method for quantifying similarity by adapting four extant similar measures, and present a method of quantifying the ratio of verbs that would need phonological conditioning due to consecutive vowels. The verbs selected are those relevant for weather forecasts for Xhosa and Zulu and newly specified as computational grammar rules. The 52 Xhosa and 49 Zulu rules share 42 rules, supporting informal impressions of their similarity. The morphosyntactic similarity reached 59.5% overall on the adapted Driver-Kroeber metric, with past tense rules only at 99.5%. This similarity score is a result of the variation in terminals mainly for the prefix of the verb.https://sacj.cs.uct.ac.za/index.php/sacj/article/view/698 |
| spellingShingle | Zola Mahlaza Catharina Maria Keet A method for measuring verb similarity for two closely related languages with application to Zulu and Xhosa South African Computer Journal |
| title | A method for measuring verb similarity for two closely related languages with application to Zulu and Xhosa |
| title_full | A method for measuring verb similarity for two closely related languages with application to Zulu and Xhosa |
| title_fullStr | A method for measuring verb similarity for two closely related languages with application to Zulu and Xhosa |
| title_full_unstemmed | A method for measuring verb similarity for two closely related languages with application to Zulu and Xhosa |
| title_short | A method for measuring verb similarity for two closely related languages with application to Zulu and Xhosa |
| title_sort | method for measuring verb similarity for two closely related languages with application to zulu and xhosa |
| url | https://sacj.cs.uct.ac.za/index.php/sacj/article/view/698 |
| work_keys_str_mv | AT zolamahlaza amethodformeasuringverbsimilarityfortwocloselyrelatedlanguageswithapplicationtozuluandxhosa AT catharinamariakeet amethodformeasuringverbsimilarityfortwocloselyrelatedlanguageswithapplicationtozuluandxhosa AT zolamahlaza methodformeasuringverbsimilarityfortwocloselyrelatedlanguageswithapplicationtozuluandxhosa AT catharinamariakeet methodformeasuringverbsimilarityfortwocloselyrelatedlanguageswithapplicationtozuluandxhosa |