基于ELAN软件的平行语料库加工处理系统设计

Design of Parallel Corpus Processing System Based on Elan Software

为实现语料信息文件的跨语言检索,建立更加稳定的数据信息编译环境,设计基于ELAN软件的平行语料库加工处理系统。利用核心处理架构,规划文档编辑模块与平行管理模块间的实际连接关系,完成平行语料库加工处理系统的硬件执行环境搭建。在此基础上,借助ELAN工具,对语料字符串匹配分词进行调试,再通过定义角色表关系的方式,完成系统的软件执行环境搭建,结合相关硬件设备结构,实现基于ELAN软件平行语料库加工处理系统的顺利应用。对比实验结果表明,与传统双语型语料库加工系统相比,平行语料库加工处理系统能够对跨语言检索信息进行精准区分,并可从中快速提取所需的数据信息,满足稳定数据信息编译环境的实际建设需求。

In order to realize the cross-language retrieval of corpus information files and establish a more stable data compilation environment, a parallel corpus processing system based on Elan software was designed. By using the core processing architecture, the actual connection relationship between document editing module and parallel management module is planned, and the hardware execution environment of parallel corpus processing system is built. On this basis, with the help of Elan tool, we debug the string matching and word segmentation of corpus. Then, by defining the role table relationship, we complete the construction of the software execution environment of the system. Combined with the structure of related hardware devices, we realize the smooth application of the parallel corpus processing system based on Elan software. The comparative experimental results show that, compared with the traditional bilingual corpus processing system, the parallel corpus processing system can accurately distinguish the cross-language retrieval information, extract the required data information quickly, and meet the actual construction requirements of stable data and information compilation environment.