Question trunks and focus extraction based on question dependency syntax conversion

Abstract

For the problems of extracting question trunks and focus extraction completely by conventional dependency syntax parsing, this paper presents a method of question trunks and focus extraction oriented to question dependency syntax conversion with the characteristics of the questions. The method defines a number of combining rules of question dependency relations. According to the rules, we do merger, conversion and removal to parts component of question syntax, and extract the question trunks and focus based on question dependency syntactic structure. The experimental results show that the proposed method of question trunks and focus extraction based on dependency syntax conversion achieved good results.

Related Papers

• → Some arguments for higher nodes in syntax: a reply to Hudson’s ‘Constituency and dependency’(1980)71 cited
• → Exploiting Synergies Between Open Resources for German Dependency Parsing, POS-tagging, and Morphological Analysis(2013)44 cited
• Easy-First Chinese POS Tagging and Dependency Parsing(2012)
• → A Simulated Shallow Dependency Parser Based on Weighted Hierarchical Structure Learning(2008)1 cited
• → A simulated shallow dependency parser based on weighted hierarchical structure learning(2008)