论文信息 - UofR at SemEval-2016 Task 8: Learning Synchronous Hyperedge Replacement Grammar for AMR Parsing

UofR at SemEval-2016 Task 8: Learning Synchronous Hyperedge Replacement Grammar for AMR Parsing

In this paper, we apply a synchronous-graphgrammar-based approach to SemEval-2016 Task 8, Meaning Representation Parsing. In particular, we learn Synchronous Hyperedge Replacement Grammar (SHRG) rules from aligned pairs of sentences and AMR graphs. Then we use Earley algorithm with cubepruning for AMR parsing given new sentences and the learned SHRG. Experiments on the evaluation dataset demonstrate that competitive results can be achieved using a SHRGbased approach.

Xiaochang Peng | Daniel Gildea | D. Gildea | Xiaochang Peng

[1] Jaime G. Carbonell,et al. A Discriminative Graph-Based Parser for the Abstract Meaning Representation , 2014, ACL.

[2] Annegret Habel,et al. Hyperedge Replacement, Graph Grammars , 1997, Handbook of Graph Grammars.

[3] Chuan Wang,et al. A Transition-based Algorithm for AMR Parsing , 2015, NAACL.

[4] Philipp Koehn,et al. Abstract Meaning Representation for Sembanking , 2013, LAW@ACL.

[5] Xiaochang Peng,et al. A Synchronous Hyperedge Replacement Grammar based approach for AMR parsing , 2015, CoNLL.

[6] Kevin Knight,et al. Smatch: an Evaluation Metric for Semantic Feature Structures , 2013, ACL.

[7] Chuan Wang,et al. Boosting Transition-based AMR Parsing with Refined Actions and Auxiliary Analyzers , 2015, ACL.

[8] Xiaochang Peng,et al. Type-based MCMC for Sampling Tree Fragments from Forests , 2014, EMNLP.

[9] Dan Roth,et al. Design Challenges and Misconceptions in Named Entity Recognition , 2009, CoNLL.

[10] David Chiang,et al. Hierarchical Phrase-Based Translation , 2007, CL.

[11] Daniel Gildea,et al. Sampling Tree Fragments from Forests , 2014, Computational Linguistics.