摘要
在自然语言处理中词性标注和词干提取是最重要的任务.文中研究与实现基于Android的维吾尔文词性标注和词干提取APP,为维吾尔语自然语言处理工作开发出了快捷和方便的标注平台,目的是通过APP对大规模语料进行词性标注和词干提取,实现了广大学员通过一部Android系统的手机随时随地参与语料标注任务,从而完成了大规模语料的标注工作,将其应用到文本分析、机器翻译、语音合成、语音翻译等研究领域.该系统的实现为低资源少数民族智能化研究工作做出了贡献.
Part-of-speech(POS)tagging and stem extracting are the most important tasks in natural language processing (NLP). A Uyghur POS tagging and stem extracting APP based on Android is researched and implemented,which develops a quick and convenient tagging platform for Uyghur NLP task. Its purpose is to carry out POS tagging and stem extracting for large- scale corpus through APP,so that the general students can participate in corpus tagging task at any time and anywhere through an Android phone,thus completing the tagging of large-scale corpus. It is applied to text analysis,machine translation,speech synthesis,speech translation and other research fields. The realization of this system has contributed to the minorities intelligent research works with low resources.
作者
帕丽旦·木合塔尔
热依曼·吐尔逊
买买提阿依甫
排孜拉·奴来海买提
MUHETAER Palidan;TUERXUN Reyiman;Maimaitiayifu;NULAIHAIMAITI Paizila(College of Information Science & Engineering,Xinjiang University,Urumqi 830046,China;Key Laboratory of Multi-Language Information Technology,Xinjiang University,Urumqi 830046,China)
出处
《现代电子技术》
北大核心
2019年第18期139-142,146,共5页
Modern Electronics Technique
基金
自治区多语种信息技术重点实验室项目(049807)
国家自然科学基金项目(U1603262)~~
关键词
安卓
词性标注
词干提取
维吾尔文
语料库
文本分析
Android
part-of-speech tagging
stem extracting
uyghur
corpus
text analysis