The Best of BothWorlds -- A Graph-based Completion Model for Transition-based Parsers
作者： Bernd Bohnet , Jonas Kuhn
DOI:
关键词: Computer science 、 Czech 、 Parsing 、 Natural language processing 、 Graph based 、 Graph (abstract data type) 、 Theoretical computer science 、 Artificial intelligence
摘要: Transition-based dependency parsers are often forced to make attachment decisions at a point when only partial information about the relevant graph configuration is available. In this paper, we describe model that takes into account complete structures as they become available rescore elements of beam, combining advantages transition-based and graph-based approaches. We also propose an efficient implementation allows for use sophisticated features show completion leads substantial increase in accuracy. apply new parser on typologically different languages such English, Chinese, Czech, German report competitive labeled unlabeled scores.
aclweb.org参考文章(40)
Xavier Carreras, Experiments with a Higher-Order Projective Dependency Parser empirical methods in natural language processing. pp. 957- 961 ,(2007)
Joakim Nivre, An efficient algorithm for projective dependency parsing international workshop/conference on parsing technologies. pp. 149- 160 ,(2003)
Yuji Matsumoto, Hiroyasu Yamada, Statistical Dependency Analysis with Support Vector Machines international workshop/conference on parsing technologies. pp. 195- 206 ,(2003)
Bernd Bohnet, Top Accuracy and Fast Dependency Parsing is not a Contradiction international conference on computational linguistics. pp. 89- 97 ,(2010)
Fernando C. N. Pereira, Ryan T. McDonald, Online Learning of Approximate Dependency Parsing Algorithms. conference of the european chapter of the association for computational linguistics. ,(2006)
Eric Xing, Andre Martins, Mario Figueiredo, Pedro Aguiar, Noah Smith, Turbo Parsers: Dependency Parsing by Approximate Variational Inference empirical methods in natural language processing. pp. 34- 44 ,(2010)
Mark Dredze, Kuzman Ganchev, Small Statistical Models by Random Feature Mixing meeting of the association for computational linguistics. pp. 19- 20 ,(2008)
Michael Elhadad, Yoav Goldberg, An Efficient Algorithm for Easy-First Non-Directional Dependency Parsing north american chapter of the association for computational linguistics. pp. 742- 750 ,(2010)
Yoav Freund, Robert E. Schapire, Large margin classification using the perceptron algorithm conference on learning theory. ,vol. 37, pp. 209- 217 ,(1998) , 10.1145/279943.279985
Bernd Bohnet, Efficient Parsing of Syntactic and Semantic Dependency Structures conference on computational natural language learning. pp. 67- 72 ,(2009) , 10.3115/1596409.1596421