Zobrazit minimální záznam

 
dc.contributor.author Rosa, Rudolf
dc.date.accessioned 2015-05-19T09:31:18Z
dc.date.available 2015-05-19T09:31:18Z
dc.date.issued 2015-05-19
dc.identifier.uri http://hdl.handle.net/11234/1-1480
dc.description MSTperl is a Perl reimplementation of the MST parser of Ryan McDonald (http://www.seas.upenn.edu/~strctlrn/MSTParser/MSTParser.html). MST parser (Maximum Spanning Tree parser) is a state-of-the-art natural language dependency parser -- a tool that takes a sentence and returns its dependency tree. In MSTperl, only some functionality was implemented; the limitations include the following: the parser is a non-projective one, curently with no possibility of enforcing the requirement of projectivity of the parse trees; only first-order features are supported, i.e. no second-order or third-order features are possible; the implementation of MIRA is that of a single-best MIRA, with a closed-form update instead of using quadratic programming. On the other hand, the parser supports several advanced features: parallel features, i.e. enriching the parser input with word-aligned sentence in other language; adding large-scale information, i.e. the feature set enriched with features corresponding to pointwise mutual information of word pairs in a large corpus (CzEng); weighted/unweighted parser model interpolation; combination of several instances of the MSTperl parser (through MST algorithm); combination of several existing parses from any parsers (through MST algorithm). The MSTperl parser is tuned for parsing Czech. Trained models are available for Czech, English and German. We can train the parser for other languages on demand, or you can train it yourself -- the guidelines are part of the documentation. The parser, together with detailed documentation, is avalable on CPAN (http://search.cpan.org/~rur/Treex-Parser-MSTperl/).
dc.description.sponsorship The research has been supported by the EU Seventh Framework Programme under grant agreement 247762 (Faust), and by the grants GAUK116310 and GA201/09/H057.
dc.language.iso ces
dc.language.iso eng
dc.publisher Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
dc.relation info:eu-repo/grantAgreement/EC/FP7/247762
dc.relation info:eu-repo/grantAgreement/EC/FP7/610516
dc.relation.replaces http://hdl.handle.net/11858/00-097C-0000-0023-7AEB-4
dc.rights Artistic License 2.0
dc.rights.uri http://opensource.org/licenses/Artistic-2.0
dc.source.uri https://ufal.mff.cuni.cz/tools/mstperl-parser
dc.subject parser
dc.subject NLP
dc.subject Treex
dc.subject parsing
dc.subject dependency
dc.title MSTperl parser (2015-05-19)
dc.type toolService
metashare.ResourceInfo#ContactInfo#PersonInfo.surname Rosa
metashare.ResourceInfo#ContactInfo#PersonInfo.givenName Rudolf
metashare.ResourceInfo#ContactInfo#PersonInfo#OrganizationInfo.organizationName Charles University in Prague, UFAL
metashare.ResourceInfo#DistributionInfo.availability unrestrictedUse
metashare.ResourceInfo#ContactInfo#PersonInfo#OrganizationInfo#CommunicationInfo.email rosa@ufal.mff.cuni.cz
metashare.ResourceInfo#ResourceComponentType#ToolServiceInfo.languageDependent true
metashare.ResourceInfo#ContentInfo.detailedType tool
dc.rights.label PUB
has.files yes
branding LINDAT / CLARIAH-CZ
contact.person Rudolf Rosa rosa@ufal.mff.cuni.cz Charles University in Prague, UFAL
sponsor European Union FP7-ICT-2009-4-247762 Faust euFunds info:eu-repo/grantAgreement/EC/FP7/247762
sponsor Grantová agentura Univerzity Karlovy v Praze GAUK 116310/2010 Anglicko-český strojový překlad s využitím hloubkové syntaxe nationalFunds
sponsor Grantová agentura České republiky GD201/09/H057 Res Informatica nationalFunds
sponsor Grantová agentura Univerzity Karlovy v Praze GAUK 15723/2014 Modelování závislostní syntaxe napříč jazyky nationalFunds
sponsor European Union FP7-ICT-2013-10-610516 Quality Translation by Deep Language Engineering Approaches (QTLeap) euFunds info:eu-repo/grantAgreement/EC/FP7/610516
sponsor Univerzita Karlova v Praze (mimo GAUK) SVV 260 224 Specifický vysokoškolský výzkum nationalFunds
files.size 83272
files.count 1


 Soubory tohoto záznamu

Licenční kategorie:
Publicly Available

Licence: Artistic License 2.0
The Open Source Initiative
Icon
Název
Treex-Parser-MSTperl-150519.tar.gz
Velikost
81.32 KB
Formát
application/x-gzip
MD5
c1547a7a762db0d713a22d5507ea06e5
 Stáhnout soubor  Náhled
 Náhled souboru  
  • Treex
    • Tool
      • Parser
        • MSTperl
          • MultiModelParser.pm10 kB
          • TrainerLabelling.pm25 kB
          • scripts
            • test_labeller_tsv.pl2 kB
            • unlabelled_test_rur.sh303 B
            • test_conll_multiplefiles_printout.pl1 kB
            • test_conll.pl1 kB
            • TagMorceEnglishCoNLL.pl1 kB
            • pcedt2conll.sh564 B
            • test_conll_multimodel_weighted_f_printout.pl1 kB
            • test_conll_treecomb_weighted_f_printout.pl2 kB
            • test_conll_multimodel_weighted.pl1 kB
            • labelled_parse_test.sh493 B
            • test_rur_conll.pl1 kB
            • test_conll_treecomb_weighted.pl2 kB
            • unlabelled_train_and_test.sh538 B
            • unlabelled_test.sh295 B
            • labeller_test.sh428 B
            • test_conll_multimodel_weighted_norm.pl1 kB
            • pdtT2conll.sh377 B
            • labeller_train_and_test.sh589 B
            • pcedt2conll_tag_and_parse_en_worsen_cs.sh898 B
            • worsen_pcedt.sh787 B
            • conll2inline.pl449 B
            • train_conll.pl855 B
            • test_conll_multimodel_weighted_f.pl1 kB
            • compare_lines.pl1 kB
            • test_conll_treecomb_weighted_f.pl2 kB
            • inline2conll.pl398 B
            • test_conll_multimodel.pl1 kB
            • pcedt2conll_td.sh545 B
            • train_labeller_tsv.pl1 kB
            • test_conll_multimodel_weighted_f_norm.pl1 kB
            • split_afun_ismember.sh332 B
            • inline_sentences_reorder.pl630 B
            • test_parse_and_label.pl2 kB
            • test_conll_parsecomb.pl1 kB
            • test_conll_multimodel_weighted_f_norm_printout.pl1 kB
            • simple_lemmas.pl708 B
            • test_conll_parsecomb_weighted.pl1 kB
            • pcedt2conll_tag_and_parse_en.sh668 B
            • test_conll_multiplefiles.pl1 kB
            • test_conll_treecomb_weighted_f_multiconf.pl2 kB
            • make_czech_tags.pl681 B
            • test_conll_multimodel_weighted_f_multiconf.pl1 kB
          • ModelUnlabelled.pm8 kB
          • Parser.pm6 kB
          • ModelLabelling.pm43 kB
          • Reader.pm2 kB
          • ModelBase.pm6 kB
          • Labeller.pm28 kB
          • t
            • train_and_test.t6 kB
            • sample_test.tsv2 kB
            • sample_train.tsv4 kB
            • sample.config7 kB
          • samples
            • treex_input.txt813 B
            • train_tsv.pl850 B
            • sample.config5 kB
            • sample_train.sh73 B
            • treex_parse.scen721 B
            • train_labeller_tsv.pl1021 B
            • sample_test.sh68 B
            • labeller_test.sh82 B
            • test_tsv.pl1 kB
            • labeller_train.sh86 B
            • sample_train.tsv4 kB
            • sample_test.tsv2 kB
            • test_labeller_tsv.pl2 kB
          • ParsedSentencesCombiner.pm3 kB
          • FeaturesControl.pm56 kB
          • Node.pm5 kB
          • Edge.pm4 kB
          • TrainerBase.pm8 kB
          • TrainerUnlabelled.pm11 kB
          • Sentence.pm18 kB
          • ModelAdditional.pm7 kB
          • Writer.pm2 kB
          • RootNode.pm1 kB
          • MultiHeteroModelParser.pm3 kB
          • ParserCombiner.pm4 kB
          • Config.pm31 kB
        • MSTperl.pm10 kB

Zobrazit minimální záznam