Slavic Forest, Norwegian Wood (scripts)
- Title:
- Slavic Forest, Norwegian Wood (scripts)
- Creator:
- Rosa, Rudolf, Zeman, Daniel, Mareček, David, and Žabokrtský, Zdeněk
- Contributor:
- European Union@@EC/H2020/644402@@HimL - Health in my Language@@euFunds@@info:eu-repo/grantAgreement/EC/H2020/644402, Ministerstvo školství, mládeže a tělovýchovy České republiky@@LM2015071@@LINDAT/CLARIN: Institut pro analýzu, zpracování a distribuci lingvistických dat@@nationalFunds@@, Grantová agentura Univerzity Karlovy v Praze@@GAUK 15723/2014@@Modelování závislostní syntaxe napříč jazyky@@nationalFunds@@, Univerzita Karlova (mimo GAUK)@@SVV 260 333@@Specifický vysokoškolský výzkum@@nationalFunds@@, and Grantová agentura České republiky@@15-10472S@@Morphologically and Syntactically Annotated Corpora of Many Languages@@nationalFunds@@
- Publisher:
- Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
- Identifier:
- http://hdl.handle.net/11234/1-1970
- Subject:
- parsing, dependency parser, universal dependencies, and cross-lingual parsing
- Type:
- suiteOfTools and toolService
- Description:
- Tools and scripts used to create the cross-lingual parsing models submitted to VarDial 2017 shared task (https://bitbucket.org/hy-crossNLP/vardial2017), as described in the linked paper. The trained UDPipe models themselves are published in a separate submission (https://lindat.mff.cuni.cz/repository/xmlui/handle/11234/1-1971). For each source (SS, e.g. sl) and target (TT, e.g. hr) language, you need to add the following into this directory: - treebanks (Universal Dependencies v1.4): SS-ud-train.conllu TT-ud-predPoS-dev.conllu - parallel data (OpenSubtitles from Opus): OpenSubtitles2016.SS-TT.SS OpenSubtitles2016.SS-TT.TT !!! If they are originally called ...TT-SS... instead of ...SS-TT..., you need to symlink them (or move, or copy) !!! - target tagging model TT.tagger.udpipe All of these can be obtained from https://bitbucket.org/hy-crossNLP/vardial2017 You also need to have: - Bash - Perl 5 - Python 3 - word2vec (https://code.google.com/archive/p/word2vec/); we used rev 41 from 15th Sep 2014 - udpipe (https://github.com/ufal/udpipe); we used commit 3e65d69 from 3rd Jan 2017 - Treex (https://github.com/ufal/treex); we used commit d27ee8a from 21st Dec 2016 The most basic setup is the sl-hr one (train_sl-hr.sh): - normalization of deprels - 1:1 word-alignment of parallel data with Monolingual Greedy Aligner - simple word-by-word translation of source treebank - pre-training of target word embeddings - simplification of morpho feats (use only Case) - and finally, training and evaluating the parser Both da+sv-no (train_ds-no.sh) and cs-sk (train_cs-sk.sh) add some cross-tagging, which seems to be useful only in specific cases (see paper for details). Moreover, cs-sk also adds more morpho features, selecting those that seem to be very often shared in parallel data. The whole pipeline takes tens of hours to run, and uses several GB of RAM, so make sure to use a powerful computer.
- Language:
- Czech, Slovak, Slovenian, Croatian, Danish, Swedish, and Norwegian
- Rights:
- GNU General Public License 2 or later (GPL-2.0)
http://opensource.org/licenses/GPL-2.0
PUB - Relation:
- info:eu-repo/grantAgreement/EC/H2020/644402
http://web.science.mq.edu.au/~smalmasi/vardial4/pdf/VarDial26.pdf - Harvested from:
- LINDAT/CLARIAH-CZ repository
- Metadata only:
- false
- Date:
- 2017-01-28
The item or associated files might be "in copyright"; review the provided rights metadata:
- GNU General Public License 2 or later (GPL-2.0)
- http://opensource.org/licenses/GPL-2.0
- PUB