短文本理解研究

王仲远; 程健鹏; 王海勋; 文继荣

doi:10.7544/issn1000-1239.2016.20150742

短文本理解研究

¹(中国人民大学信息学院北京 100872)
²(微软亚洲研究院北京 100080)
³(牛津大学计算机科学学院英国牛津 OX1 3QD)
⁴(Facebook 美国加利福尼亚州门洛帕克市 94025) (zhy.wang@microsoft.com)

基金项目: 国家“九七三”基础研究发展计划基金项目(2014CB340403);中央高校基本科研业务费专项资金(14XNLF05)

详细信息

中图分类号: TP391
计量
- 文章访问数: 3478
- HTML全文浏览量: 2
- PDF下载量: 3290
出版历程
- 发布日期: 2016-01-31

Short Text Understanding: A Survey

¹(School of Information, Renmin University of China, Beijing 100872)
²(Microsoft Research Asia, Beijing 100080)
²(Department of Computer Science, Oxford University, OXford, UK OX1 3QD)
⁴(Facebook, Menlo Park, CA, USA 94025)

摘要

摘要: 短文本理解是一项对于机器智能至关重要但又充满挑战的任务.这项任务有益于众多应用场景，如搜索引擎、自动问答、广告和推荐系统.完成这些应用的首要步骤是将输入文本转化为机器可以诠释的形式，即帮助机器“理解”短文本的含义.基于这一目标，许多方法利用外来知识源来解决短文本中语境信息不足的问题.通过总结短文本理解领域的相关工作，介绍了基于向量的短文本理解框架.同时，探讨了短文本理解领域未来的研究方向.
- 知识挖掘 /
- 短文本理解 /
- 概念化 /
- 语义计算
Abstract: Short text understanding is an important but challenging task relevant for machine intelligence. The task can potentially benefit various online applications, such as search engines, automatic question-answering, online advertising and recommendation systems. In all these applications, the necessary first step is to transform an input text into a machine-interpretable representation, namely to “understand” the short text. To achieve this goal, various approaches have been proposed to leverage external knowledge sources as a complement to the inadequate contextual information accompanying short texts. This survey reviews current progress in short text understanding with a focus on the vector based approaches, which aim to derive the vectorial encoding for a short text. We also explore a few potential research topics in the field of short text understanding.
- knowledge mining /
- short text understanding /
- conceptualization /
- semantic computing