« Previous |
41 - 49 of 49
|
Next »
Number of results to display per page
Search Results
42. THEaiTRobot 1.0
- Creator:
- Rosa, Rudolf, Dušek, Ondřej, Kocmi, Tom, Mareček, David, Musil, Tomáš, Schmidtová, Patrícia, Jurko, Dominik, Bojar, Ondřej, Hrbek, Daniel, Košťák, David, Kinská, Martina, Nováková, Marie, Doležal, Josef, and Vosecká, Klára
- Publisher:
- Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), The Švanda Theatre in Smíchov, and The Academy of Performing Arts in Prague, Theatre Faculty (DAMU)
- Type:
- tool and toolService
- Subject:
- theatre and natural language generation
- Language:
- English and Czech
- Description:
- The THEaiTRobot 1.0 tool allows the user to interactively generate scripts for individual theatre play scenes. The tool is based on GPT-2 XL generative language model, using the model without any fine-tuning, as we found that with a prompt formatted as a part of a theatre play script, the model usually generates continuation that retains the format. We encountered numerous problems when generating the script in this way. We managed to tackle some of the problems with various adjustments, but some of them remain to be solved in a future version. THEaiTRobot 1.0 was used to generate the first THEaiTRE play, "AI: Když robot píše hru" ("AI: When a robot writes a play").
- Rights:
- The MIT License (MIT), http://opensource.org/licenses/mit-license.php, and PUB
43. THEaiTRobot 2.0
- Creator:
- Rosa, Rudolf, Dušek, Ondřej, Kocmi, Tom, Mareček, David, Musil, Tomáš, Schmidtová, Patrícia, Jurko, Dominik, Bojar, Ondřej, Hrbek, Daniel, Košťák, David, Kinská, Martina, Nováková, Marie, Doležal, Josef, Vosecká, Klára, Zakhtarenko, Alisa, and Obaid, Saad
- Publisher:
- Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), The Švanda Theatre in Smíchov, and The Academy of Performing Arts in Prague, Theatre Faculty (DAMU)
- Type:
- tool and toolService
- Subject:
- theatre and natural language generation
- Language:
- English and Czech
- Description:
- The THEaiTRobot 2.0 tool allows the user to interactively generate scripts for individual theatre play scenes. The previous version of the tool (http://hdl.handle.net/11234/1-3507) was based on GPT-2 XL generative language model, using the model without any fine-tuning, as we found that with a prompt formatted as a part of a theatre play script, the model usually generates continuation that retains the format. The current version also uses vanilla GPT-2 by default, but can also instead use a GPT-2 medium model fine-tuned on theatre play scripts (as well as film and TV series scripts). Apart from the basic "flat" generation using a theatrical starting prompt and the script model, the tool also features a second, hierarchical variant, where in the first step, a play synopsis is generated from its title using a synopsis model (GPT-2 medium fine-tuned on synopses of theatre plays, as well as film, TV series and book synopses). The synopsis is then used as input for the second stage, which uses the script model. The choice of models to use is done by setting the MODEL variable in start_server.sh and start_syn_server.sh THEaiTRobot 2.0 was used to generate the second THEaiTRE play, "Permeation/Prostoupení".
- Rights:
- The MIT License (MIT), http://opensource.org/licenses/mit-license.php, and PUB
44. UMC 0.1: Czech-Russian-English Multilingual Corpus
- Creator:
- Klyueva, Natalia and Bojar, Ondřej
- Publisher:
- Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
- Type:
- text and corpus
- Subject:
- multi-language corpus
- Language:
- Czech
- Description:
- UMC 0.1 Czech-English-Russian is a multilingual parallel corpus of texts in Czech, Russian and English languages with automatic pairwise sentence alignments. The primary aim of UMC is to extend the set of languages covered by the corpus CzEng mainly for the purposes of machine translation. All the texts were downloaded from a single source — The Project Syndicate (Copyright: Project Syndicate 1995-2008), which contains a huge collection of high-quality news articles and commentaries. We were given the permission to use the texts for research and non-commercial purposes. and FP6-IST-5-034291-STP (EuroMatrix)
- Rights:
- Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0), http://creativecommons.org/licenses/by-nc-nd/3.0/, and PUB
45. Urdu Monolingual Corpus
- Creator:
- Jawaid, Bushra, Kamran, Amir, and Bojar, Ondřej
- Publisher:
- Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
- Type:
- text, corpus, other, and lexicalConceptualResource
- Subject:
- Urdu, monolingual data, annotated data, and corpus
- Language:
- Urdu
- Description:
- We release a sizeable monolingual Urdu corpus automatically tagged with part-of-speech tags. We extend the work of Jawaid and Bojar (2012) who use three different taggers and then apply a voting scheme to disambiguate among the different choices suggested by each tagger. We run this complex ensemble on a large monolingual corpus and release the both plain and tagged corpora. and it is supported by the MosesCore project sponsored by the European Commission’s Seventh Framework Programme (Grant Number 288487).
- Rights:
- Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0), http://creativecommons.org/licenses/by-nc-sa/3.0/, and PUB
46. WMT 13 Test Set
- Creator:
- Hoang, Duc Tam and Bojar, Ondřej
- Publisher:
- Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
- Type:
- text and corpus
- Subject:
- test data, parallel corpus, and Vietnamese
- Language:
- Vietnamese, Czech, English, German, French, Spanish, and Russian
- Description:
- We provide the Vietnamese version of the multi-lingual test set from WMT 2013 [1] competition. The Vietnamese version was manually translated from English. For completeness, this record contains the 3000 sentences in all the WMT 2013 original languages (Czech, English, French, German, Russian and Spanish), extended with our Vietnamese version. Test set is used in [2] to evaluate translation between Czech, English and Vietnamese. References 1. http://www.statmt.org/wmt13/evaluation-task.html 2. Duc Tam Hoang and Ondřej Bojar, The Prague Bulletin of Mathematical Linguistics. Volume 104, Issue 1, Pages 75--86, ISSN 1804-0462. 9/2015
- Rights:
- Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0), http://creativecommons.org/licenses/by-nc-sa/4.0/, and PUB
47. WMT 2011 Testing Set
- Creator:
- Galuščáková, Petra and Bojar, Ondřej
- Publisher:
- Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL)
- Type:
- text and corpus
- Subject:
- WMT, test data, and Slovak
- Language:
- Slovak, Czech, and English
- Description:
- Testing set from WMT 2011 [1] competition, manually translated from Czech and English into Slovak. Test set contains 3003 sentences in Czech, Slovak and English. Test set is described in [2]. References: [1] http://www.statmt.org/wmt11/evaluation-task.html [2] Petra Galuščáková and Ondřej Bojar. Improving SMT by Using Parallel Data of a Closely Related Language. In Human Language Technologies - The Baltic Perspective - Proceedings of the Fifth International Conference Baltic HLT 2012, volume 247 of Frontiers in AI and Applications, pages 58-65, Amsterdam, Netherlands, October 2012. IOS Press. and The work on this project was supported by the grant EuroMatrixPlus (FP7-ICT- 2007-3-231720 of the EU and 7E09003 of the Czech Republic)
- Rights:
- Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0), http://creativecommons.org/licenses/by-nc-sa/3.0/, and PUB
48. WMT16 Tuning Shared Task Models (Czech-to-English)
- Creator:
- Kamran, Amir, Jawaid, Bushra, Bojar, Ondřej, and Stanojevic, Milos
- Publisher:
- Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL) and University of Amsterdam, ILLC
- Type:
- text and corpus
- Subject:
- WMT16, machine translation, tuning, baseline models, and shared task
- Language:
- Czech and English
- Description:
- The item contains models to tune for the WMT16 Tuning shared task for Czech-to-English. CzEng 1.6pre (http://ufal.mff.cuni.cz/czeng/czeng16pre) corpus is used for the training of the translation models. The data is tokenized (using Moses tokenizer), lowercased and sentences longer than 60 words and shorter than 4 words are removed before training. Alignment is done using fast_align (https://github.com/clab/fast_align) and the standard Moses pipeline is used for training. Two 5-gram language models are trained using KenLM: one only using the CzEng English data and the other is trained using all available English mono data for WMT except Common Crawl. Also included are two lexicalized bidirectional reordering models, word based and hierarchical, with msd conditioned on both source and target of processed CzEng.
- Rights:
- Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0), http://creativecommons.org/licenses/by-nc-sa/4.0/, and PUB
49. WMT16 Tuning Shared Task Models (English-to-Czech)
- Creator:
- Kamran, Amir, Jawaid, Bushra, Bojar, Ondřej, and Stanojevic, Milos
- Publisher:
- Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL) and University of Amsterdam, ILLC
- Type:
- text and corpus
- Subject:
- WMT16, machine translation, tuning, baseline models, and shared task
- Language:
- English and Czech
- Description:
- This item contains models to tune for the WMT16 Tuning shared task for English-to-Czech. CzEng 1.6pre (http://ufal.mff.cuni.cz/czeng/czeng16pre) corpus is used for the training of the translation models. The data is tokenized (using Moses tokenizer), lowercased and sentences longer than 60 words and shorter than 4 words are removed before training. Alignment is done using fast_align (https://github.com/clab/fast_align) and the standard Moses pipeline is used for training. Two 5-gram language models are trained using KenLM: one only using the CzEng Czech data and the other is trained using all available Czech mono data for WMT except Common Crawl. Also included are two lexicalized bidirectional reordering models, word based and hierarchical, with msd conditioned on both source and target of processed CzEng.
- Rights:
- Creative Commons - Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0), http://creativecommons.org/licenses/by-nc-sa/4.0/, and PUB