Paper: Recent Advances in Dependency Parsing

ACL ID N10-4004
Title Recent Advances in Dependency Parsing
Venue Human Language Technologies
Session Tutorial Abstracts
Year 2010

, pages 7–8, Los Angeles, California, June 2010. c©2010 Association for Computational Linguistics Recent Advances in Dependency Parsing Qin Iris Wang, AT&T Interactive Yue Zhang, Oxford Data-driven (statistical) approaches have been playing an increasingly prominent role in parsing since the 1990s. In recent years, there has been a growing interest in dependency-based as opposed to constituency-based approaches to syntactic parsing, with application to a wide range of research areas and different languages. Graph-based and transition-based methods are the two dominant data-driven approaches to dependency parsing. In a graph-based model, it defines a space of candidate dependency trees for a given sentence. Each candidate tree is scored via a local or global scoring function. The pars...