Skip to search
Skip to main content
Skip to first result
Search
Search Results
Creator:
Rosa, Rudolf , Zeman, Daniel , Mareček, David , and Žabokrtský, Zdeněk
Publisher:
Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
Type:
suiteOfTools and toolService
Subject:
parsing , dependency parser , universal dependencies , and cross-lingual parsing
Language:
Czech , Slovak , Slovenian , Croatian , Danish , Swedish , and Norwegian
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.
Rights:
GNU General Public License 2 or later (GPL-2.0) , http://opensource.org/licenses/GPL-2.0 , and PUB
Creator:
Nivre, Joakim , Abrams, Mitchell , Agić, Željko , Ahrenberg, Lars , Aleksandravičiūtė, Gabrielė , Antonsen, Lene , Aplonova, Katya , Aranzabe, Maria Jesus , Arutie, Gashaw , Asahara, Masayuki , Ateyah, Luma , Attia, Mohammed , Atutxa, Aitziber , Augustinus, Liesbeth , Badmaeva, Elena , Ballesteros, Miguel , Banerjee, Esha , Bank, Sebastian , Barbu Mititelu, Verginica , Basmov, Victoria , Bauer, John , Bellato, Sandra , Bengoetxea, Kepa , Berzak, Yevgeni , Bhat, Irshad Ahmad , Bhat, Riyaz Ahmad , Biagetti, Erica , Bick, Eckhard , Bielinskienė, Agnė , Blokland, Rogier , Bobicev, Victoria , Boizou, Loïc , Borges Völker, Emanuel , Börstell, Carl , Bosco, Cristina , Bouma, Gosse , Bowman, Sam , Boyd, Adriane , Brokaitė, Kristina , Burchardt, Aljoscha , Candito, Marie , Caron, Bernard , Caron, Gauthier , Cebiroğlu Eryiğit, Gülşen , Cecchini, Flavio Massimiliano , Celano, Giuseppe G. A. , Čéplö, Slavomír , Cetin, Savas , Chalub, Fabricio , Choi, Jinho , Cho, Yongseok , Chun, Jayeol , Cinková, Silvie , Collomb, Aurélie , Çöltekin, Çağrı , Connor, Miriam , Courtin, Marine , Davidson, Elizabeth , de Marneffe, Marie-Catherine , de Paiva, Valeria , Diaz de Ilarraza, Arantza , Dickerson, Carly , Dione, Bamba , Dirix, Peter , Dobrovoljc, Kaja , Dozat, Timothy , Droganova, Kira , Dwivedi, Puneet , Eckhoff, Hanne , Eli, Marhaba , Elkahky, Ali , Ephrem, Binyam , Erjavec, Tomaž , Etienne, Aline , Farkas, Richárd , Fernandez Alcalde, Hector , Foster, Jennifer , Freitas, Cláudia , Fujita, Kazunori , Gajdošová, Katarína , Galbraith, Daniel , Garcia, Marcos , Gärdenfors, Moa , Garza, Sebastian , Gerdes, Kim , Ginter, Filip , Goenaga, Iakes , Gojenola, Koldo , Gökırmak, Memduh , Goldberg, Yoav , Gómez Guinovart, Xavier , González Saavedra, Berta , Grioni, Matias , Grūzītis, Normunds , Guillaume, Bruno , Guillot-Barbance, Céline , Habash, Nizar , Hajič, Jan , Hajič jr., Jan , Hà Mỹ, Linh , Han, Na-Rae , Harris, Kim , Haug, Dag , Heinecke, Johannes , Hennig, Felix , Hladká, Barbora , Hlaváčová, Jaroslava , Hociung, Florinel , Hohle, Petter , Hwang, Jena , Ikeda, Takumi , Ion, Radu , Irimia, Elena , Ishola, Ọlájídé , Jelínek, Tomáš , Johannsen, Anders , Jørgensen, Fredrik , Kaşıkara, Hüner , Kaasen, Andre , Kahane, Sylvain , Kanayama, Hiroshi , Kanerva, Jenna , Katz, Boris , Kayadelen, Tolga , Kenney, Jessica , Kettnerová, Václava , Kirchner, Jesse , Köhn, Arne , Kopacewicz, Kamil , Kotsyba, Natalia , Kovalevskaitė, Jolanta , Krek, Simon , Kwak, Sookyoung , Laippala, Veronika , Lambertino, Lorenzo , Lam, Lucia , Lando, Tatiana , Larasati, Septina Dian , Lavrentiev, Alexei , Lee, John , Lê Hồng, Phương , Lenci, Alessandro , Lertpradit, Saran , Leung, Herman , Li, Cheuk Ying , Li, Josie , Li, Keying , Lim, KyungTae , Li, Yuan , Ljubešić, Nikola , Loginova, Olga , Lyashevskaya, Olga , Lynn, Teresa , Macketanz, Vivien , Makazhanov, Aibek , Mandl, Michael , Manning, Christopher , Manurung, Ruli , Mărănduc, Cătălina , Mareček, David , Marheinecke, Katrin , Martínez Alonso, Héctor , Martins, André , Mašek, Jan , Matsumoto, Yuji , McDonald, Ryan , McGuinness, Sarah , Mendonça, Gustavo , Miekka, Niko , Misirpashayeva, Margarita , Missilä, Anna , Mititelu, Cătălin , Miyao, Yusuke , Montemagni, Simonetta , More, Amir , Moreno Romero, Laura , Mori, Keiko Sophie , Morioka, Tomohiko , Mori, Shinsuke , Moro, Shigeki , Mortensen, Bjartur , Moskalevskyi, Bohdan , Muischnek, Kadri , Murawaki, Yugo , Müürisep, Kaili , Nainwani, Pinkey , Navarro Horñiacek, Juan Ignacio , Nedoluzhko, Anna , Nešpore-Bērzkalne, Gunta , Nguyễn Thị, Lương , Nguyễn Thị Minh, Huyền , Nikaido, Yoshihiro , Nikolaev, Vitaly , Nitisaroj, Rattima , Nurmi, Hanna , Ojala, Stina , Olúòkun, Adédayọ̀ , Omura, Mai , Osenova, Petya , Östling, Robert , Øvrelid, Lilja , Partanen, Niko , Pascual, Elena , Passarotti, Marco , Patejuk, Agnieszka , Paulino-Passos, Guilherme , Peljak-Łapińska, Angelika , Peng, Siyao , Perez, Cenel-Augusto , Perrier, Guy , Petrova, Daria , Petrov, Slav , Piitulainen, Jussi , Pirinen, Tommi A , Pitler, Emily , Plank, Barbara , Poibeau, Thierry , Popel, Martin , Pretkalniņa, Lauma , Prévost, Sophie , Prokopidis, Prokopis , Przepiórkowski, Adam , Puolakainen, Tiina , Pyysalo, Sampo , Rääbis, Andriela , Rademaker, Alexandre , Ramasamy, Loganathan , Rama, Taraka , Ramisch, Carlos , Ravishankar, Vinit , Real, Livy , Reddy, Siva , Rehm, Georg , Rießler, Michael , Rimkutė, Erika , Rinaldi, Larissa , Rituma, Laura , Rocha, Luisa , Romanenko, Mykhailo , Rosa, Rudolf , Rovati, Davide , Roșca, Valentin , Rudina, Olga , Rueter, Jack , Sadde, Shoval , Sagot, Benoît , Saleh, Shadi , Salomoni, Alessio , Samardžić, Tanja , Samson, Stephanie , Sanguinetti, Manuela , Särg, Dage , Saulīte, Baiba , Sawanakunanon, Yanin , Schneider, Nathan , Schuster, Sebastian , Seddah, Djamé , Seeker, Wolfgang , Seraji, Mojgan , Shen, Mo , Shimada, Atsuko , Shirasu, Hiroyuki , Shohibussirri, Muh , Sichinava, Dmitry , Silveira, Natalia , Simi, Maria , Simionescu, Radu , Simkó, Katalin , Šimková, Mária , Simov, Kiril , Smith, Aaron , Soares-Bastos, Isabela , Spadine, Carolyn , Stella, Antonio , Straka, Milan , Strnadová, Jana , Suhr, Alane , Sulubacak, Umut , Suzuki, Shingo , Szántó, Zsolt , Taji, Dima , Takahashi, Yuta , Tamburini, Fabio , Tanaka, Takaaki , Tellier, Isabelle , Thomas, Guillaume , Torga, Liisi , Trosterud, Trond , Trukhina, Anna , Tsarfaty, Reut , Tyers, Francis , Uematsu, Sumire , Urešová, Zdeňka , Uria, Larraitz , Uszkoreit, Hans , Vajjala, Sowmya , van Niekerk, Daniel , van Noord, Gertjan , Varga, Viktor , Villemonte de la Clergerie, Eric , Vincze, Veronika , Wallin, Lars , Walsh, Abigail , Wang, Jing Xian , Washington, Jonathan North , Wendt, Maximilan , Williams, Seyi , Wirén, Mats , Wittern, Christian , Woldemariam, Tsegay , Wong, Tak-sum , Wróblewska, Alina , Yako, Mary , Yamazaki, Naoki , Yan, Chunxiao , Yasuoka, Koichi , Yavrumyan, Marat M. , Yu, Zhuoran , Žabokrtský, Zdeněk , Zeldes, Amir , Zeman, Daniel , Zhang, Manying , and Zhu, Hanzhi
Publisher:
Universal Dependencies Consortium
Type:
text and corpus
Subject:
treebank , dependency , syntax , morphology , harmonized annotation , interset , universal tagset , and stanford dependencies
Language:
Ancient Greek (to 1453) , Arabic , Basque , Bulgarian , Croatian , Czech , Danish , Dutch , English , Estonian , Finnish , French , German , Gothic , Modern Greek (1453-) , Hebrew , Hindi , Hungarian , Indonesian , Irish , Italian , Japanese , Latin , Norwegian , Church Slavic , Persian , Polish , Portuguese , Romanian , Slovenian , Spanish , Swedish , Tamil , Catalan , Chinese , Galician , Kazakh , Latvian , Russian , Turkish , Coptic , Sanskrit , Slovak , Ukrainian , Uighur , Vietnamese , Belarusian , Korean , Lithuanian , Urdu , Russia Buriat , Northern Kurdish , Northern Sami , Upper Sorbian , Afrikaans , Yue Chinese , Marathi , Serbian , Swedish Sign Language , Telugu , Amharic , Armenian , Breton , Faroese , Komi-Zyrian , Nigerian Pidgin , Old French (842-ca. 1400) , Tagalog , Thai , Warlpiri , Yoruba , Akkadian , Bambara , Erzya , Maltese , Welsh , Wolof , Assyrian Neo-Aramaic , Literary Chinese , Old Russian , Karelian , and Mbyá Guaraní
Description:
Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008).
Rights:
Licence Universal Dependencies v2.4 , https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.4 , and PUB
Creator:
Zeman, Daniel , Nivre, Joakim , Abrams, Mitchell , Aepli, Noëmi , Agić, Željko , Ahrenberg, Lars , Aleksandravičiūtė, Gabrielė , Antonsen, Lene , Aplonova, Katya , Aranzabe, Maria Jesus , Arutie, Gashaw , Asahara, Masayuki , Ateyah, Luma , Attia, Mohammed , Atutxa, Aitziber , Augustinus, Liesbeth , Badmaeva, Elena , Ballesteros, Miguel , Banerjee, Esha , Bank, Sebastian , Barbu Mititelu, Verginica , Basmov, Victoria , Batchelor, Colin , Bauer, John , Bellato, Sandra , Bengoetxea, Kepa , Berzak, Yevgeni , Bhat, Irshad Ahmad , Bhat, Riyaz Ahmad , Biagetti, Erica , Bick, Eckhard , Bielinskienė, Agnė , Blokland, Rogier , Bobicev, Victoria , Boizou, Loïc , Borges Völker, Emanuel , Börstell, Carl , Bosco, Cristina , Bouma, Gosse , Bowman, Sam , Boyd, Adriane , Brokaitė, Kristina , Burchardt, Aljoscha , Candito, Marie , Caron, Bernard , Caron, Gauthier , Cavalcanti, Tatiana , Cebiroğlu Eryiğit, Gülşen , Cecchini, Flavio Massimiliano , Celano, Giuseppe G. A. , Čéplö, Slavomír , Cetin, Savas , Chalub, Fabricio , Choi, Jinho , Cho, Yongseok , Chun, Jayeol , Cignarella, Alessandra T. , Cinková, Silvie , Collomb, Aurélie , Çöltekin, Çağrı , Connor, Miriam , Courtin, Marine , Davidson, Elizabeth , de Marneffe, Marie-Catherine , de Paiva, Valeria , de Souza, Elvis , Diaz de Ilarraza, Arantza , Dickerson, Carly , Dione, Bamba , Dirix, Peter , Dobrovoljc, Kaja , Dozat, Timothy , Droganova, Kira , Dwivedi, Puneet , Eckhoff, Hanne , Eli, Marhaba , Elkahky, Ali , Ephrem, Binyam , Erina, Olga , Erjavec, Tomaž , Etienne, Aline , Evelyn, Wograine , Farkas, Richárd , Fernandez Alcalde, Hector , Foster, Jennifer , Freitas, Cláudia , Fujita, Kazunori , Gajdošová, Katarína , Galbraith, Daniel , Garcia, Marcos , Gärdenfors, Moa , Garza, Sebastian , Gerdes, Kim , Ginter, Filip , Goenaga, Iakes , Gojenola, Koldo , Gökırmak, Memduh , Goldberg, Yoav , Gómez Guinovart, Xavier , González Saavedra, Berta , Griciūtė, Bernadeta , Grioni, Matias , Grūzītis, Normunds , Guillaume, Bruno , Guillot-Barbance, Céline , Habash, Nizar , Hajič, Jan , Hajič jr., Jan , Hämäläinen, Mika , Hà Mỹ, Linh , Han, Na-Rae , Harris, Kim , Haug, Dag , Heinecke, Johannes , Hennig, Felix , Hladká, Barbora , Hlaváčová, Jaroslava , Hociung, Florinel , Hohle, Petter , Hwang, Jena , Ikeda, Takumi , Ion, Radu , Irimia, Elena , Ishola, Ọlájídé , Jelínek, Tomáš , Johannsen, Anders , Jørgensen, Fredrik , Juutinen, Markus , Kaşıkara, Hüner , Kaasen, Andre , Kabaeva, Nadezhda , Kahane, Sylvain , Kanayama, Hiroshi , Kanerva, Jenna , Katz, Boris , Kayadelen, Tolga , Kenney, Jessica , Kettnerová, Václava , Kirchner, Jesse , Klementieva, Elena , Köhn, Arne , Kopacewicz, Kamil , Kotsyba, Natalia , Kovalevskaitė, Jolanta , Krek, Simon , Kwak, Sookyoung , Laippala, Veronika , Lambertino, Lorenzo , Lam, Lucia , Lando, Tatiana , Larasati, Septina Dian , Lavrentiev, Alexei , Lee, John , Lê Hồng, Phương , Lenci, Alessandro , Lertpradit, Saran , Leung, Herman , Li, Cheuk Ying , Li, Josie , Li, Keying , Lim, KyungTae , Liovina, Maria , Li, Yuan , Ljubešić, Nikola , Loginova, Olga , Lyashevskaya, Olga , Lynn, Teresa , Macketanz, Vivien , Makazhanov, Aibek , Mandl, Michael , Manning, Christopher , Manurung, Ruli , Mărănduc, Cătălina , Mareček, David , Marheinecke, Katrin , Martínez Alonso, Héctor , Martins, André , Mašek, Jan , Matsumoto, Yuji , McDonald, Ryan , McGuinness, Sarah , Mendonça, Gustavo , Miekka, Niko , Misirpashayeva, Margarita , Missilä, Anna , Mititelu, Cătălin , Mitrofan, Maria , Miyao, Yusuke , Montemagni, Simonetta , More, Amir , Moreno Romero, Laura , Mori, Keiko Sophie , Morioka, Tomohiko , Mori, Shinsuke , Moro, Shigeki , Mortensen, Bjartur , Moskalevskyi, Bohdan , Muischnek, Kadri , Munro, Robert , Murawaki, Yugo , Müürisep, Kaili , Nainwani, Pinkey , Navarro Horñiacek, Juan Ignacio , Nedoluzhko, Anna , Nešpore-Bērzkalne, Gunta , Nguyễn Thị, Lương , Nguyễn Thị Minh, Huyền , Nikaido, Yoshihiro , Nikolaev, Vitaly , Nitisaroj, Rattima , Nurmi, Hanna , Ojala, Stina , Ojha, Atul Kr. , Olúòkun, Adédayọ̀ , Omura, Mai , Osenova, Petya , Östling, Robert , Øvrelid, Lilja , Partanen, Niko , Pascual, Elena , Passarotti, Marco , Patejuk, Agnieszka , Paulino-Passos, Guilherme , Peljak-Łapińska, Angelika , Peng, Siyao , Perez, Cenel-Augusto , Perrier, Guy , Petrova, Daria , Petrov, Slav , Phelan, Jason , Piitulainen, Jussi , Pirinen, Tommi A , Pitler, Emily , Plank, Barbara , Poibeau, Thierry , Ponomareva, Larisa , Popel, Martin , Pretkalniņa, Lauma , Prévost, Sophie , Prokopidis, Prokopis , Przepiórkowski, Adam , Puolakainen, Tiina , Pyysalo, Sampo , Qi, Peng , Rääbis, Andriela , Rademaker, Alexandre , Ramasamy, Loganathan , Rama, Taraka , Ramisch, Carlos , Ravishankar, Vinit , Real, Livy , Reddy, Siva , Rehm, Georg , Riabov, Ivan , Rießler, Michael , Rimkutė, Erika , Rinaldi, Larissa , Rituma, Laura , Rocha, Luisa , Romanenko, Mykhailo , Rosa, Rudolf , Rovati, Davide , Roșca, Valentin , Rudina, Olga , Rueter, Jack , Sadde, Shoval , Sagot, Benoît , Saleh, Shadi , Salomoni, Alessio , Samardžić, Tanja , Samson, Stephanie , Sanguinetti, Manuela , Särg, Dage , Saulīte, Baiba , Sawanakunanon, Yanin , Schneider, Nathan , Schuster, Sebastian , Seddah, Djamé , Seeker, Wolfgang , Seraji, Mojgan , Shen, Mo , Shimada, Atsuko , Shirasu, Hiroyuki , Shohibussirri, Muh , Sichinava, Dmitry , Silveira, Aline , Silveira, Natalia , Simi, Maria , Simionescu, Radu , Simkó, Katalin , Šimková, Mária , Simov, Kiril , Smith, Aaron , Soares-Bastos, Isabela , Spadine, Carolyn , Stella, Antonio , Straka, Milan , Strnadová, Jana , Suhr, Alane , Sulubacak, Umut , Suzuki, Shingo , Szántó, Zsolt , Taji, Dima , Takahashi, Yuta , Tamburini, Fabio , Tanaka, Takaaki , Tellier, Isabelle , Thomas, Guillaume , Torga, Liisi , Trosterud, Trond , Trukhina, Anna , Tsarfaty, Reut , Tyers, Francis , Uematsu, Sumire , Urešová, Zdeňka , Uria, Larraitz , Uszkoreit, Hans , Utka, Andrius , Vajjala, Sowmya , van Niekerk, Daniel , van Noord, Gertjan , Varga, Viktor , Villemonte de la Clergerie, Eric , Vincze, Veronika , Wallin, Lars , Walsh, Abigail , Wang, Jing Xian , Washington, Jonathan North , Wendt, Maximilan , Williams, Seyi , Wirén, Mats , Wittern, Christian , Woldemariam, Tsegay , Wong, Tak-sum , Wróblewska, Alina , Yako, Mary , Yamazaki, Naoki , Yan, Chunxiao , Yasuoka, Koichi , Yavrumyan, Marat M. , Yu, Zhuoran , Žabokrtský, Zdeněk , Zeldes, Amir , Zhang, Manying , and Zhu, Hanzhi
Publisher:
Universal Dependencies Consortium
Type:
text and corpus
Subject:
treebank , dependency , syntax , morphology , harmonized annotation , interset , universal tagset , and stanford dependencies
Language:
Ancient Greek (to 1453) , Arabic , Basque , Bulgarian , Croatian , Czech , Danish , Dutch , English , Estonian , Finnish , French , German , Gothic , Modern Greek (1453-) , Hebrew , Hindi , Hungarian , Indonesian , Irish , Italian , Japanese , Latin , Norwegian , Church Slavic , Persian , Polish , Portuguese , Romanian , Slovenian , Spanish , Swedish , Tamil , Catalan , Chinese , Galician , Kazakh , Latvian , Russian , Turkish , Coptic , Sanskrit , Slovak , Ukrainian , Uighur , Vietnamese , Belarusian , Korean , Lithuanian , Urdu , Russia Buriat , Northern Kurdish , Northern Sami , Upper Sorbian , Afrikaans , Yue Chinese , Marathi , Serbian , Swedish Sign Language , Telugu , Amharic , Armenian , Breton , Faroese , Komi-Zyrian , Nigerian Pidgin , Old French (842-ca. 1400) , Tagalog , Thai , Warlpiri , Yoruba , Akkadian , Bambara , Erzya , Maltese , Welsh , Wolof , Assyrian Neo-Aramaic , Literary Chinese , Old Russian , Karelian , Mbyá Guaraní , Bhojpuri , Komi-Permyak , Livvi , Moksha , Scottish Gaelic , Skolt Sami , and Swiss German
Description:
Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research from a language typology perspective. The annotation scheme is based on (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014), Google universal part-of-speech tags (Petrov et al., 2012), and the Interset interlingua for morphosyntactic tagsets (Zeman, 2008).
Rights:
Licence Universal Dependencies v2.5 , https://lindat.mff.cuni.cz/repository/xmlui/page/licence-UD-2.5 , and PUB