Towards an unsupervised morphological segmenter for isiXhosa

2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA) Pub Date : 2019-01-01 DOI:10.1109/ROBOMECH.2019.8704816]

Lulamile Mzamo, A.S. Helberg, Sonja E. Bosch

{"title":"Towards an unsupervised morphological segmenter for isiXhosa","authors":"Lulamile Mzamo, A.S. Helberg, Sonja E. Bosch","doi":"10.1109/ROBOMECH.2019.8704816]","DOIUrl":null,"url":null,"abstract":"In this paper, branching entropy techniques and isiXhosa language heuristics are adapted to develop unsupervised morphological segmenters for isiXhosa. An overview of isiXhosa segmentation issues is given, followed by a discussion on previous work in automated segmentation, and segmentation of isiXhosa in particular. Two unsupervised isiXhosa segmenters are presented and compared to a random minimum baseline and Morfessor-Baseline, a standard in unsupervised word segmentation. Morfessor-Baseline outperforms both isiXhosa segmenters at 79.10% boundary identification accuracy. The IsiXhosa Branching Entropy Segmenter (XBES) performance varies depending on the segmentation mode used, with a maximum of 73.39%. The IsiXhosa Heuristic Maximum Likelihood Segmenter (XHMLS) achieves 72.42%. The study suggests that unsupervised isiXhosa morphological segmentation is feasible with better optimization of the current attempts.","PeriodicalId":344332,"journal":{"name":"2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ROBOMECH.2019.8704816]","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 3

Abstract

In this paper, branching entropy techniques and isiXhosa language heuristics are adapted to develop unsupervised morphological segmenters for isiXhosa. An overview of isiXhosa segmentation issues is given, followed by a discussion on previous work in automated segmentation, and segmentation of isiXhosa in particular. Two unsupervised isiXhosa segmenters are presented and compared to a random minimum baseline and Morfessor-Baseline, a standard in unsupervised word segmentation. Morfessor-Baseline outperforms both isiXhosa segmenters at 79.10% boundary identification accuracy. The IsiXhosa Branching Entropy Segmenter (XBES) performance varies depending on the segmentation mode used, with a maximum of 73.39%. The IsiXhosa Heuristic Maximum Likelihood Segmenter (XHMLS) achieves 72.42%. The study suggests that unsupervised isiXhosa morphological segmentation is feasible with better optimization of the current attempts.

查看原文本刊更多论文

一种无监督形态分词的研究

本文采用分支熵技术和isiXhosa语言启发式方法来开发isiXhosa语言的无监督形态分词。概述了isiXhosa分割问题，然后讨论了以前在自动分割方面的工作，特别是isiXhosa分割。提出了两个无监督isiXhosa分词器，并将其与随机最小基线和无监督分词标准Morfessor-Baseline进行了比较。morprof - baseline以79.10%的边界识别准确率优于两种isiXhosa分割器。IsiXhosa分支熵分割器(XBES)的性能根据所使用的分割模式而变化，最高可达73.39%。IsiXhosa启发式最大似然分割(XHMLS)达到72.42%。研究表明，通过对现有方法的优化，无监督isiXhosa形态学分割是可行的。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA)

自引率

0.00%

发文量