Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Experimental Space
Results
Error Analysis
Conclusion
References
All Topics
Computer Science

Benchmarking of Statistical Dependency Parsers for French

Profile image of Marie CanditoMarie Candito

2010

Abstract

We compare the performance of three statistical parsing architectures on the problem of deriving typed dependency structures for French. The architectures are based on PCFGs with latent variables, graph-based dependency parsing and transition-based dependency parsing, respectively. We also study the influence of three types of lexical information: lemmas, morphological features, and word clusters. The results show that all three systems achieve competitive performance, with a best labeled attachment score over 88%. All three parsers benefit from the use of automatically derived lemmas, while morphological features seem to be less important. Word clusters have a positive effect primarily on the latent variable parser.

Related papers

Comparing advanced graph-based and transition-based dependency parsers
Bernd Bohnet

In this paper, we compare a higher order graph-based parser and a transitionbased parser with beam search. These parsers provide a higher accuracy than a second order MST parser and a deterministic transition-based parser. We apply and compare the output on languages, which have not been in the research focus of Shared Tasks. The parser are implemented in a uniform framework. The transitionbased parser was newley implemented and we revised the graph-based parser. The graph-based parser has to our knowlege the highest published scores for French and Czech with 90.40 and 81.43 labeled accuracy score.

View PDFchevron_right
Application of feature propagation to dependency parsing
Koldo Gojenola, Kepa Bengoetxea

… of the 11th International Conference on …, 2009

View PDFchevron_right
Improving data-driven dependency parsing using large-scale LFG grammars
Rajeev Sangal

Proceedings of the ACL-IJCNLP 2009 Conference Short Papers on - ACL-IJCNLP '09, 2009

The paper describes a data driven dependency parsing approach which uses information about the clauses in a sentence to improve the parser performance. The clausal information is added automatically using a partial parser. We demonstrate the experiments on Hindi, a morphologically rich, free-word-order language, using a modified version of MSTParser. We did all the experiments on the ICON 2009 parsing contest data. We achieved an improvement of 0.87% and 0.77% in unlabeled attachment and labeled attachment accuracies respectively over the baseline parsing accuracies.

View PDFchevron_right
Dependency parsing resources for French: Converting acquired lexical functional grammar F-Structure annotations and parsing F-Structures directly
Natalie Schluter

2009

View PDFchevron_right
Lemmatization and lexicalized statistical parsing of morphologically rich languages: the case of French
Marie Candito

2010

This paper shows that training a lexicalized parser on a lemmatized morphologically-rich treebank such as the French Treebank slightly improves parsing results. We also show that lemmatizing a similar in size subset of the English Penn Treebank has almost no effect on parsing performance with gold lemmas and leads to a small drop of performance when automatically assigned lemmas and POS tags are used. This highlights two facts: (i) lemmatization helps to reduce lexicon data-sparseness issues for French, (ii) it also makes the parsing process sensitive to correct assignment of POS tags to unknown words.

View PDFchevron_right
MaltParser: A language-independent system for data-driven dependency parsing
GULSEN ERYIGIT

Scandinavian Journal of Economics, 2007

View PDFchevron_right

References (41)

  1. Abeillé, A. and N. Barrier. 2004. Enriching a french treebank. In LREC'04.
  2. Bikel, D. M. 2002. Design of a multi-lingual, parallel- processing statistical parsing engine. In HLT-02.
  3. Brown, P., V. Della Pietra, P. Desouza, J. Lai, and R. Mercer. 1992. Class-based n-gram models of natural language. Computational linguistics, 18(4).
  4. Buchholz, S. and E. Marsi. 2006. CoNLL-X shared task on multilingual dependency parsing. In CoNLL 2006.
  5. Candito, M. and B. Crabbé. 2009. Improving gener- ative statistical parsing with semi-supervised word clustering. In IWPT'09.
  6. Candito, M. and D. Seddah. 2010. Parsing word clus- ters. In NAACL/HLT Workshop SPMRL 2010.
  7. Candito, M., B. Crabbé, and P. Denis. 2010. Statis- tical french dependency parsing : treebank conver- sion and rst results. In LREC 2010.
  8. Carroll, J., E. Briscoe, and A. Sanlippo. 1998. Parser evaluation: A survey and a new proposal. In LREC 1998.
  9. Cer, D., M.-C. de Marneffe, D. Jurafsky, and C. Man- ning. 2010. Parsing to stanford dependencies: Trade-offs between speed and accuracy. In LREC 2010.
  10. Charniak, E. 2000. A maximum entropy inspired parser. In NAACL 2000.
  11. Crabbé, B. and M. Candito. 2008. Expériences d'analyse syntaxique statistique du français. In TALN 2008.
  12. de la Clergerie, E. V., C. Ayache, G. de Chalendar, G. Francopoulo, C. Gardent, and P. Paroubek. 2008. Large scale production of syntactic annotations for french. In First International Workshop on Auto- mated Syntactic Annotations for Interoperable Lan- guage Resources.
  13. de Marneffe, M.-C., B. MacCartney, and C. D. Man- ning. 2006. Generating typed dependency parses from phrase structure parses. In LREC 2006.
  14. Denis, P. and B. Sagot. 2009. Coupling an an- notated corpus and a morphosyntactic lexicon for state-of-the-art pos tagging with less human effort. In PACLIC 2009.
  15. Eisner, J. 1996. Three new probabilistic models for dependency parsing: An exploration. In COLING 1996.
  16. Fan, R.-E., K.-W. Chang, C.-J. Hsieh, X.-R. Wang, and C.-J. Lin. 2008. LIBLINEAR: A library for large linear classication. Journal of Machine Learning Research, 9.
  17. Kahane, S., A. Nasr, and O. Rambow. 1998.
  18. Pseudo-projectivity: A polynomially parsable non- projective dependency grammar. In ACL/COLING 1998.
  19. Klein, D. and C. D. Manning. 2003. Accurate unlexi- calized parsing. In ACL 2003.
  20. Koo, T., X. Carreras, and M. Collins. 2008. Sim- ple semi-supervised dependency parsing. In ACL- 08:HLT.
  21. Kübler, S. 2008. The PaGe 2008 shared task on pars- ing german. In ACL-08 Workshop on Parsing Ger- man.
  22. Lin, D. 1995. A dependency-based method for evalu- ating broad-coverage parsers. In IJCAI-95.
  23. Magerman, D. M. 1995. Statistical decision-tree mod- els for parsing. In ACL 1995.
  24. Matsuzaki, T., Y. Miyao, and J. Tsujii. 2005. Proba- bilistic cfg with latent annotations. In ACL 2005.
  25. McDonald, R. and J. Nivre. 2007. Characterizing the errors of data-driven dependency parsing mod- els. In EMNLP-CoNLL 2007.
  26. McDonald, R. and F. Pereira. 2006. Online learning of approximate dependency parsing algorithms. In EACL 2006.
  27. McDonald, R., K. Lerman, and F. Pereira. 2006. Mul- tilingual dependency analysis with a two-stage dis- criminative parser. In CoNLL 2006.
  28. McDonald, R. 2006. Discriminative Learning and Spanning Tree Algorithms for Dependency Parsing. Ph.D. thesis, University of Pennsylvania.
  29. Nivre, J., Johan Hall, and Jens Nilsson. 2006. Malt- parser: A data-driven parser-generator for depen- dency parsing. In LREC 2006.
  30. Nivre, J., J. Hall, S. Kübler, R. McDonald, J. Nils- son, S. Riedel, and D. Yuret. 2007. The CoNLL 2007 shared task on dependency parsing. In CoNLL Shared Task of EMNLP-CoNLL 2007.
  31. Nivre, J. 2006. Inductive Dependency Parsing. Springer.
  32. Nivre, J. 2008. Algorithms for deterministic incre- mental dependency parsing. Computational Lin- guistics, 34.
  33. Paroubek, P., L.-G. Pouillot, I. Robba, and A. Vilnat. 2005. Easy : Campagne d'évaluation des analy- seurs syntaxiques. In TALN 2005, EASy workshop : campagne d'évaluation des analyseurs syntaxiques.
  34. Petrov, S. and D. Klein. 2007. Improved inference for unlexicalized parsing. In NAACL-07: HLT.
  35. Petrov, S., L. Barrett, R. Thibaux, and D. Klein. 2006. Learning accurate, compact, and interpretable tree annotation. In ACL 2006.
  36. Sagot, B. 2010. The Lefff, a freely available and large- coverage morphological and syntactic lexicon for french. In LREC 2010.
  37. Schluter, N. and J. van Genabith. 2009. Dependency parsing resources for french: Converting acquired lfg f-structure. In NODALIDA 2009.
  38. Seddah, D., M. Candito, and B. Crabbé. 2009. Cross parser evaluation and tagset variation: a french tree- bank study. In IWPT 2009.
  39. Seddah, D., G. Chrupa!a, O. Cetinoglu, J. van Gen- abith, and M. Candito. 2010. Lemmatization and statistical lexicalized parsing of morphologically- rich languages. In NAACL/HLT Workshop SPMRL 2010.
  40. Tsarfaty, R. 2006. Integrated morphological and syn- tactic disambiguation for modern hebrew. In COL- ING/ACL 2006 Student Research Workshop.
  41. Yamada, H. and Y. Matsumoto. 2003. Statistical de- pendency analysis with support vector machines. In IWPT 2003.

Related papers

Statistical french dependency parsing: Treebank conversion and first results
Pascal Denis

2010

We first describe the automatic conversion of the French Treebank (Abeillé and , a constituency treebank, into typed projective dependency trees. In order to evaluate the overall quality of the resulting dependency treebank, and to quantify the cases where the projectivity constraint leads to wrong dependencies, we compare a subset of the converted treebank to manually validated dependency trees. We then compare the performance of two treebank-trained parsers that output typed dependency parses. The first parser is the MST parser , which we directly train on dependency trees. The second parser is a combination of the Berkeley parser (Petrov et al., 2006) and a functional role labeler: trained on the original constituency treebank, the Berkeley parser first outputs constituency trees, which are then labeled with functional roles, and then converted into dependency trees. We found that used in combination with a high-accuracy French POS tagger, the MST parser performs a little better for unlabeled dependencies (UAS=90.3% versus 89.6%), and better for labeled dependencies (LAS=87.6% versus 85.6%).

View PDFchevron_right
Probabilistic lexical generalization for French dependency parsing
Marie Candito

This paper investigates the impact on French dependency parsing of lexical generalization methods beyond lemmatization and morphological analysis. A distributional thesaurus is created from a large text corpus and used for distributional clustering and WordNet automatic sense ranking. The standard approach for lexical generalization in parsing is to map a word to a single generalized class, either replacing the word with the class or adding a new feature for the class. We use a richer framework that allows for probabilistic generalization, with a word represented as a probability distribution over a space of generalized classes: lemmas, clusters, or synsets. Probabilistic lexical information is introduced into parser feature vectors by modifying the weights of lexical features. We obtain improvements in parsing accuracy with some lexical generalization configurations in experiments run on the French Treebank and two out-of-domain treebanks, with slightly better performance for the probabilistic lexical generalization approach compared to the standard single-mapping approach.

View PDFchevron_right
Parsing Poorly Standardized Language Dependency on Old French
Sophie Prevost

2014

This paper presents results of dependency parsing of Old French, a language which is poorly standardized at the lexical level, and which displays a relatively free word order. The work is carried out on five distinct sample texts extracted from the dependency treebank Syntactic Reference Corpus of Medieval French (SRCMF). Following Achim Stein's previous work, we have trained the Mate parser on each sub-corpus and cross-validated the results. We show that the parsing efficiency is diminished by the greater lexical variation of Old French compared to parse results on modern French. In order to improve the result of the POS tagging step in the parsing process, we applied a pre-treatment to the data, comparing two distinct strategies: one using a slightly post-treated version of the TreeTagger trained on Old French by Stein, and a CRF trained on the texts, enriched with external resources. The CRF version outperforms every other approach.

View PDFchevron_right
On Different Approaches to Syntactic Analysis Into Bi-Lexical Dependencies An Empirical Comparison of Direct, PCFG-Based, and HPSG-Based Parsers
Stephan Oepen

Journal of Language Modelling, 2016

We compare three different approaches to parsing into syntactic, bi-lexical dependencies for English: a 'direct' data-driven dependency parser, a statistical phrase structure parser, and a hybrid, 'deep' grammar-driven parser. The analyses from the latter two are post-converted to bilexical dependencies. Through this 'reduction' of all three approaches to syntactic dependency parsers, we determine empirically what performance can be obtained for a common set of dependency types for English, across a broad variety of domains. In doing so, we observe what trade-offs apply along three dimensions, accuracy, efficiency, and resilience to domain variation. Our results suggest that the hand-built grammar in one of our parsers helps in both accuracy and cross-domain performance.

View PDFchevron_right
Inspecting the structural biases of dependency parsing algorithms
Michael Elhadad

2010

This paper presents an algorithm for unsupervised co-occurrence based parsing that improves and extends existing approaches. The proposed algorithm induces a contextfree grammar of the language in question in an iterative manner. The resulting structure of a sentence will be given as a hierarchical arrangement of constituents. Although this algorithm does not use any a priori knowledge about the language, it is able to detect heads, modifiers and a phrase type's different compound composition possibilities. For evaluation purposes, the algorithm is applied to manually annotated part-of-speech tags (POS tags) as well as to word classes induced by an unsupervised part-of-speech tagger.

View PDFchevron_right

Related topics

  • Computer Science
    • 580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved