DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4
Hits 21 – 40 of 73

21
Deep Universal Dependencies 2.4
Zeman, Daniel; Droganova, Kira. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2019
BASE
Show details
22
Universal Dependencies 2.2
In: https://hal.archives-ouvertes.fr/hal-01930733 ; 2018 (2018)
BASE
Show details
23
CoNLL 2017 and 2018 Shared Task Blind and Preprocessed Test Data
Zeman, Daniel; Straka, Milan. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2018
BASE
Show details
24
Universal Dependencies 2.3
Nivre, Joakim; Abrams, Mitchell; Agić, Željko. - : Universal Dependencies Consortium, 2018
BASE
Show details
25
English-Urdu Religious Parallel Corpus
Jawaid, Bushra; Zeman, Daniel. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2018
BASE
Show details
26
Universal Dependencies 2.2
Nivre, Joakim; Abrams, Mitchell; Agić, Željko. - : Universal Dependencies Consortium, 2018
BASE
Show details
27
Artificial Treebank with Ellipsis
Droganova, Kira; Zeman, Daniel; Kanerva, Jenna. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2018
BASE
Show details
28
Morphological Analyzer for Shipibo-Konibo
Cardenas Acosta, Ronald; Zeman, Daniel. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2018
BASE
Show details
29
Prague Dependency Treebank 3.5
Hajič, Jan; Bejček, Eduard; Bémová, Alevtina. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2018
BASE
Show details
30
CoNLL 2018 Shared Task System Outputs
Zeman, Daniel; Potthast, Martin; Duthoo, Elie. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2018
BASE
Show details
31
Challenges in Converting the Index Thomisticus Treebank into Universal Dependencies
Zeman, Daniel; Cecchini, Flavio Massimiliano; Passarotti, Marco (orcid:0000-0002-9806-7187). - : The Association for Computational Linguistics, 2018. : country:BEL, 2018. : place:Bruxelles, Belgium, 2018
BASE
Show details
32
Universal Dependencies 2.1
In: https://hal.inria.fr/hal-01682188 ; 2017 (2017)
BASE
Show details
33
Open SDP 1.2
Flickinger, Dan; Hajič, Jan; Ivanova, Angelina. - : Oslo University, 2017. : Charles University, 2017
BASE
Show details
34
Slavic Forest, Norwegian Wood (scripts)
Rosa, Rudolf; Zeman, Daniel; Mareček, David; Žabokrtský, Zdeněk. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2017
Abstract: 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.
Keyword: cross-lingual parsing; dependency parser; parsing; universal dependencies
URL: http://hdl.handle.net/11234/1-1970
BASE
Hide details
35
CoNLL 2017 Shared Task - Automatically Annotated Raw Texts and Word Embeddings
Ginter, Filip; Hajič, Jan; Luotolahti, Juhani. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2017
BASE
Show details
36
Universal Dependencies 2.0 alpha (obsolete)
Nivre, Joakim; Agić, Željko; Ahrenberg, Lars. - : Universal Dependencies Consortium, 2017
BASE
Show details
37
CoNLL 2017 Shared Task System Outputs
Zeman, Daniel; Potthast, Martin; Straka, Milan. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2017
BASE
Show details
38
Universal Dependencies 2.0
Nivre, Joakim; Agić, Željko; Ahrenberg, Lars. - : Universal Dependencies Consortium, 2017
BASE
Show details
39
Universal Dependencies 2.0 – CoNLL 2017 Shared Task Development and Test Data
Nivre, Joakim; Agić, Željko; Ahrenberg, Lars. - : Universal Dependencies Consortium, 2017
BASE
Show details
40
Slavic Forest, Norwegian Wood (models)
Rosa, Rudolf; Zeman, Daniel; Mareček, David. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2017
BASE
Show details

Page: 1 2 3 4

Catalogues
0
0
4
0
0
0
0
Bibliographies
7
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
65
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern