Semantics based text matching for unstructured text documents

非结构化文本文档的基于语义的文本匹配

• 批准号: 500745-2016
• 负责人: Du, Weichang
• 金额: $ 1.82万
• 依托单位: University of New Brunswick
• 依托单位国家: 加拿大
• 项目类别: Engage Grants Program
• 财政年份: 2016
• 资助国家: 加拿大
• 起止时间: 2016-01-01 至 2017-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=608271
• 关键词: Semantics; based; text; matching; unstructured

In this project our aim is to develop techniques that can find matches between job postings that are in natural language text and in descriptive format and job seeker profiles that are also in free-text format without much accessible structured content. The unstructured and natural language form of data poses challenges for the accurate matching and ranking in this domain. Research challenges include (i) vocabulary mismatch within the job postings and job seeker profiles, (ii) the processing of the interaction logs that are curated as a result of the visits that both job seekers and recruiters make on the website, and (iii) the possibility of processing interaction logs for the purpose of understanding the demand and trend in the job market for certain skill sets or qualifications. The research work and required development will be carried out in close concert with the industrial partner BC Jobs Online Inc.

在这个项目中，我们的目标是开发技术，可以找到在自然语言文本和描述性格式的求职者配置文件，也是在自由文本格式没有太多的访问结构化内容之间的匹配。数据的非结构化和自然语言形式对该领域的准确匹配和排名提出了挑战。研究的挑战包括：（i）招聘信息和求职者简介中的词汇不匹配;（ii）处理求职者和招聘人员在网站上访问的互动日志;以及（iii）处理互动日志以了解就业市场对某些技能或资格的需求和趋势的可能性。研究工作和所需的开发将与工业合作伙伴BC Jobs Online Inc.密切合作。