Faster Parsing by Supertagger Adaptation

We propose a novel self-training method for a parser which uses a lexicalised grammar and supertagger, focusing on increasing the speed of the parser rather than its accuracy. The idea is to train the supertagger on large amounts of parser output, so that the supertagger can learn to supply the supertags that the parser will eventually choose as part of the highest-scoring derivation. Since the supertagger supplies fewer supertags overall, the parsing speed is increased. We demonstrate the effectiveness of the method using a CCG supertagger and parser, obtaining significant speed increases on newspaper text with no loss in accuracy. We also show that the method can be used to adapt the CCG parser to new domains, obtaining accuracy and speed improvements for Wikipedia and biomedical text.

[1]  Stephen Clark,et al.  Porting a lexicalized-grammar parser to the biomedical domain , 2009, J. Biomed. Informatics.

[2]  Treebank Penn,et al.  Linguistic Data Consortium , 1999 .

[3]  Mary Dalrymple,et al.  The PARC 700 Dependency Bank , 2003, LINC@EACL.

[4]  James R. Curran,et al.  Wide-Coverage Efficient Statistical Parsing with CCG and Log-Linear Models , 2007, Computational Linguistics.

[5]  James R. Curran,et al.  Weighted Mutual Exclusion Bootstrapping for Domain Independent Lexicon and Template Acquisition , 2008, ALTA.

[6]  Ted Briscoe,et al.  Evaluating the Accuracy of an Unlexicalized Statistical Parser on the PARC DepBank , 2006, ACL.

[7]  Stephen Clark,et al.  Adapting a Lexicalized-Grammar Parser to Contrasting Domains , 2008, EMNLP.

[8]  D K Smith,et al.  Numerical Optimization , 2001, J. Oper. Res. Soc..

[9]  Andy Way,et al.  Supertagged Phrase-Based Statistical Machine Translation , 2007, ACL.

[10]  Fei Xia,et al.  Some Experiments on Indicators of Parsing Complexity for Lexicalized Grammars , 2000, ELSPS.

[11]  Tapio Salakoski,et al.  On the unification of syntactic annotations under the Stanford dependency scheme: A case study on BioInfer and GENIA , 2007, BioNLP@ACL.

[12]  James R. Curran,et al.  Bootstrapping POS-taggers using unlabelled data , 2003, CoNLL.

[13]  Srinivas Bangalore,et al.  Supertagging: An Approach to Almost Parsing , 1999, CL.

[14]  Jun'ichi Tsujii,et al.  GENIA corpus - a semantically annotated corpus for bio-textmining , 2003, ISMB.

[15]  Anoop Sarkar,et al.  Applying Co-Training Methods to Statistical Parsing , 2001, NAACL.

[16]  Eugene Charniak,et al.  Reranking and Self-Training for Parser Adaptation , 2006, ACL.

[17]  Christopher D. Manning,et al.  Generating Typed Dependency Parses from Phrase Structure Parses , 2006, LREC.

[18]  Gertjan van Noord.  Learning Efficient Parsing , 2009, EACL.

[19]  Nancy Chinchor,et al.  Statistical Significance of MUC-6 Results , 1995, MUC.

[20]  Koby Crammer,et al.  Ultraconservative Online Algorithms for Multiclass Problems , 2001, J. Mach. Learn. Res..

[21]  Brian Roark,et al.  Pipeline Iteration , 2007, ACL.

[22]  J. Darroch,et al.  Generalized Iterative Scaling for Log-Linear Models , 1972 .

[23]  Michael Collins,et al.  Discriminative Reranking for Natural Language Parsing , 2000, CL.

[24]  Jun'ichi Tsujii,et al.  HPSG Supertagging: A Sequence Labeling View , 2009, IWPT.

[25]  Mark Steedman,et al.  CCGbank: A Corpus of CCG Derivations and Dependency Structures Extracted from the Penn Treebank , 2007, CL.

[26]  Eugene Charniak,et al.  Effective Self-Training for Parsing , 2006, NAACL.

[27]  Srinivas Bangalore,et al.  Reranking an n-gram supertagger , 2002, TAG+.

[28]  Daniel Gildea,et al.  Corpus Variation and Parser Performance , 2001, EMNLP.

[29]  Timothy Baldwin,et al.  Multilingual Deep Lexical Acquisition for HPSGs via Supertagging , 2006, EMNLP.

[30]  Beatrice Santorini,et al.  Building a Large Annotated Corpus of English: The Penn Treebank , 1993, CL.

[31]  James Richard Curran,et al.  From distributional to semantic similarity , 2004 .

[32]  Srinivas Bangalore,et al.  New Models for Improving Supertag Disambiguation , 1999, EACL.

[33]  James R. Curran,et al.  The Importance of Supertagging for Wide-Coverage CCG Parsing , 2004, COLING.

[34]  Adwait Ratnaparkhi,et al.  A Maximum Entropy Model for Part-Of-Speech Tagging , 1996, EMNLP.

[35]  Mark Steedman,et al.  Bootstrapping statistical parsers from small datasets , 2003, EACL.

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

[37]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[38]  Jimmy J. Lin,et al.  Web question answering: is more always better? , 2002, SIGIR '02.

[39]  Anoop Sarkar.  Combining Supertagging and Lexicalized Tree-Adjoining Grammar Parsing∗ , 2006 .