缅甸语命名实体识别的比较研究

2020 23rd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA) Pub Date : 2020-11-05 DOI:10.1109/O-COCOSDA50338.2020.9295004

Tin Latt Nandar, Thinn Lai Soe, K. Soe

{"title":"缅甸语命名实体识别的比较研究","authors":"Tin Latt Nandar, Thinn Lai Soe, K. Soe","doi":"10.1109/O-COCOSDA50338.2020.9295004","DOIUrl":null,"url":null,"abstract":"This paper represents the development of the Myanmar Named Entity Recognition (NER) system using Conditional Random Fields (CRFs). In order to develop the system, a manually annotated Named Entities (NEs) corpus - collected from Myanmar news websites and Asia Language Treebank(ALT)-Parallel-Corpus has been used. We compare the performance of the system getting syllable-based input to the one getting character-based input. We observed that training data has more impact on the performance of the system. The experimental results show that the syllable-based system performs better than the character-based system. It achieves that Precision, Recall and F1-score values of 93.62%, 91.64% and 92.62% respectively.","PeriodicalId":385266,"journal":{"name":"2020 23rd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"A Comparative Study of Named Entity Recognition on Myanmar Language\",\"authors\":\"Tin Latt Nandar, Thinn Lai Soe, K. Soe\",\"doi\":\"10.1109/O-COCOSDA50338.2020.9295004\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper represents the development of the Myanmar Named Entity Recognition (NER) system using Conditional Random Fields (CRFs). In order to develop the system, a manually annotated Named Entities (NEs) corpus - collected from Myanmar news websites and Asia Language Treebank(ALT)-Parallel-Corpus has been used. We compare the performance of the system getting syllable-based input to the one getting character-based input. We observed that training data has more impact on the performance of the system. The experimental results show that the syllable-based system performs better than the character-based system. It achieves that Precision, Recall and F1-score values of 93.62%, 91.64% and 92.62% respectively.\",\"PeriodicalId\":385266,\"journal\":{\"name\":\"2020 23rd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)\",\"volume\":\"82 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-11-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2020 23rd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/O-COCOSDA50338.2020.9295004\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 23rd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/O-COCOSDA50338.2020.9295004","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

摘要

本文介绍了使用条件随机场(CRFs)的缅甸命名实体识别(NER)系统的发展。为了开发该系统，使用了人工注释的命名实体(NEs)语料库-收集自缅甸新闻网站和亚洲语言树库(ALT)-平行语料库。我们比较了基于音节输入的系统和基于字符输入的系统的性能。我们观察到训练数据对系统性能的影响更大。实验结果表明，基于音节的系统比基于字符的系统性能更好。准确率(Precision)为93.62%，召回率(Recall)为91.64%，F1-score为92.62%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

A Comparative Study of Named Entity Recognition on Myanmar Language

This paper represents the development of the Myanmar Named Entity Recognition (NER) system using Conditional Random Fields (CRFs). In order to develop the system, a manually annotated Named Entities (NEs) corpus - collected from Myanmar news websites and Asia Language Treebank(ALT)-Parallel-Corpus has been used. We compare the performance of the system getting syllable-based input to the one getting character-based input. We observed that training data has more impact on the performance of the system. The experimental results show that the syllable-based system performs better than the character-based system. It achieves that Precision, Recall and F1-score values of 93.62%, 91.64% and 92.62% respectively.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2020 23rd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)

自引率

0.00%

发文量