基于结构检索的汉语介动搭配知识库构建  

Construction of Preposition-verb Knowledge Base Based on Structure Retrieval

作　　者：王诚文 饶高琦[2] 荀恩东[3] WANG Chengwen;RAO Gaoqi;XUN Endong(School of International Cultural Exchange,Central University of Finance and Economics,Beijing 100081,China;Research Institute of International Chinese Language Education,Beijing Language and Culture University,Beijing 100083,China;School of Information Science,Beijing Language and Culture University,Beijing 100083,China)

机构地区：[1]中央财经大学国际文化交流学院,北京100081 [2]北京语言大学汉语国际教育研究院,北京100083 [3]北京语言大学信息科学学院,北京100083

出　　处：《中文信息学报》2023年第7期23-31,共9页Journal of Chinese Information Processing

基　　金：国家自然科学基金(62076038)。

摘　　要：以往的介词知识库构建重视介词语义和介宾的搭配研究,鲜有对介动搭配进行系统研究及知识获取的工作。而汉语介词发达及动词是句子中心的特征决定了介动搭配研究的重要性。该文基于结构检索技术,充分借助短语结构属性和结构信息,从大规模语料中抽取介动搭配16033对,并提出了介动搭配紧密度的度量方法,初步分析证明该方法远优于依靠绝对频次进行搭配度量的方法。In contrast to the well addressed prepositional semantic and referential collocation,there had been few systematic research on knowledge extraction and knowledge-base construction for preposition-verb collocations.The study of preposition-verb collocations is especially crucial in that Chinese prepositions are well-developed and the Chinese sentences are centered around verbs.This paper extracts 16033 pairs of preposition-verb collocations from a large-scale corpus via a technology of structure retrieval according to the phrase structure attributes.A method for measuring the closeness of a preposition-verb collocation is also described,which is preliminarily revealed to be superior to the raw frequency.

关 键 词：介动搭配 结构检索 介动紧密度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]