...
首页> 外文期刊>Indian Journal of Computer Science and Engineering >HANDLING AVIATION OOV WORDS FOR MACHINE TRANSLATION AND CORPUS CREATION
【24h】

HANDLING AVIATION OOV WORDS FOR MACHINE TRANSLATION AND CORPUS CREATION

机译:机器翻译和语料库创建处理航空OOV单词

获取原文
           

摘要

The Indian aviation industry has been one of the fastest growing in the world since the last decade. Aviation experts anticipate it to be the largest in the world by 2030. The accelerated growth in passenger number has been influential enough to encourage more job opportunities in the industry. The anticipated exponential growth also envisions increase in the usage of aviation OOV words and phrases. For communicating the various proceedings and news through the mainstream and social media, these aviation words have become more frequent nowadays. The aviation domain is heavily dependent on the use of OOV words, which, in turn, are structured words molded to fit the aviation domain. This causes a huge problem during the conversion from English to other languages using machine translation (MT). This paper explores the problems encountered during translation of such sentences and suggests how these sentences can be pre-processed before being fed into the MT software for better translations. This paper also investigates how these structured and OOV words can be handled in the English language itself, before being converted to any other language and surveys the prospects of maneuvering this tool to create a bilingual corpus for Machine Translation applications.
机译:自过去十年以来,印度航空业一直是世界上增长最快的行业之一。航空专家预计到2030年将成为世界上最大的。乘客股的加速增长一直有可能鼓励更多在行业中的工作机会。预期的指数增长也设想了航空OOV单词和短语的使用量增加。通过主流和社交媒体沟通各种程序和新闻,现在这些航空词已经变得更加频繁。航空域严重依赖于OOV单词的使用,这反过来又是模塑成适于航空域的结构的单词。这在使用机器翻译(MT)转换到其他语言时会导致巨大的问题。本文探讨了此类句子的翻译过程中遇到的问题,并提出了在进入MT软件之前可以预处理这些句子的问题,以便更好地翻译。本文还调查了这些结构化和OOV单词如何以英语语言自身处理,然后转换为任何其他语言并调查机动该工具的前景,以创建机器翻译应用程序的双语语料库。

著录项

获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号