论文信息 - Linköping: Cubic-Time Graph Parsing with a Simple Scoring Scheme

Linköping: Cubic-Time Graph Parsing with a Simple Scoring Scheme

We turn the Eisner algorithm for parsing to projective dependency trees into a cubictime algorithm for parsing to a restricted class of directed graphs. To extend the algorithm into a data-driven parser, we combine it with an edge-factored feature model and online learning. We report and discuss results on the SemEval-2014 Task 8 data sets (Oepen et al., 2014).

Marco Kuhlmann

[1] Giorgio Satta,et al. Efficient Parsing for Bilexical Context-Free Grammars and Head Automaton Grammars , 1999, ACL.

[2] Weiwei Sun,et al. Peking: Profiling Syntactic Tree Parsing Techniques for Semantic Graph Parsing , 2014, SemEval@COLING.

[3] Michael Collins,et al. Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms , 2002, EMNLP.

[4] Stephan Oepen,et al. SemEval 2014 Task 8: Broad-Coverage Semantic Dependency Parsing , 2014, *SEMEVAL.

[5] Stuart M. Shieber,et al. Principles and Implementation of Deductive Parsing , 1994, J. Log. Program..

[6] Stephan Oepen,et al. Broad-Coverage Semantic Dependency Parsing , 2014 .

[7] Bernd Bohnet,et al. Very high accuracy and fast dependency parsing is not a contradiction , 2010, COLING 2010.

[8] Koby Crammer,et al. Online Large-Margin Training of Dependency Parsers , 2005, ACL.