The system Česílko (language data and software tools) was first developed as an answer to a growing need of translation and localisation from one source language to many target languages. The starting system belonged to the Shallow Parse, Shallow Transfer Rule-Based Machine Translation – (RBMT) paradigm and it was designed primarily for translation of related languages. The latest implementation of the system uses a stochastic ranker; so technically it belongs to the hybrid machine translation paradigm, using stochastic methods combined with the traditional Shallow Transfer RBMT methods. The system has been stripped of the accompanying language resources due to copyright restrictions. The data that is available is just for demonstrative purposes.
Chared is a software tool which can detect character encoding of a text document provided the language of the document is known. The language of the text has to be specified as an input parameter so that the corresponding language model can be used. The package contains models for a wide range of languages (currently 57 --- covering all major languages). Furthermore, it provides a training script to learn models for additional languages using a set of user supplied sample html pages in the given language. The detection algorithm is based on determining similarity of byte trigrams vectors. In general, chared should be more accurate than other character encoding detection tools with no language constraints. This is an important advantage allowing precise character decoding needed for building large textual corpora. The tool has been used for building corpora in American Spanish, Arabic, Czech, French, Japanese, Russian, Tajik, and six Turkic languages consisting of 70 billions tokens altogether. Chared is an open source software, licensed under New BSD License and available for download (including the source code) at http://code.google.com/p/chared/. The research leading to this piece of software was published in POMIKÁLEK, Jan a Vít SUCHOMEL. chared: Character Encoding Detection with a Known Language. In Aleš Horák, Pavel Rychlý. RASLAN 2011. 5. vyd. Brno, Czech Republic: Tribun EU, 2011. od s. 125-129, 5 s. ISBN 978-80-263-0077-9. and PRESEMT, Lexical Computing Ltd
The `corpipe23-corefud1.1-231206` is a `mT5-large`-based multilingual model for coreference resolution usable in CorPipe 23 (https://github.com/ufal/crac2023-corpipe). It is released under the CC BY-NC-SA 4.0 license.
The model is language agnostic (no _corpus id_ on input), so it can be used to predict coreference in any `mT5` language (for zero-shot evaluation, see the paper). However, note that the empty nodes must be present already on input, they are not predicted (the same settings as in the CRAC23 shared task).
Software for corpus linguists and text/data mining enthusiasts. The CorpusExplorer combines over 45 interactive visualizations under a user-friendly interface. Routine tasks such as text acquisition, cleaning or tagging are completely automated. The simple interface supports the use in university teaching and leads users/students to fast and substantial results. The CorpusExplorer is open for many standards (XML, CSV, JSON, R, etc.) and also offers its own software development kit (SDK).
Source code available at https://github.com/notesjor/corpusexplorer2.0
CUBBITT En-Cs translation models, exported via TensorFlow Serving, available in the Lindat translation service (https://lindat.mff.cuni.cz/services/translation/).
Models are compatible with Tensor2tensor version 1.6.6.
For details about the model training (data, model hyper-parameters), please contact the archive maintainer.
Evaluation on newstest2014 (BLEU):
en->cs: 27.6
cs->en: 34.4
(Evaluated using multeval: https://github.com/jhclark/multeval)
CUBBITT En-Fr translation models, exported via TensorFlow Serving, available in the Lindat translation service (https://lindat.mff.cuni.cz/services/translation/).
Models are compatible with Tensor2tensor version 1.6.6.
For details about the model training (data, model hyper-parameters), please contact the archive maintainer.
Evaluation on newstest2014 (BLEU):
en->fr: 38.2
fr->en: 36.7
(Evaluated using multeval: https://github.com/jhclark/multeval)
CUBBITT En-Pl translation models, exported via TensorFlow Serving, available in the Lindat translation service (https://lindat.mff.cuni.cz/services/translation/).
Models are compatible with Tensor2tensor version 1.6.6.
For details about the model training (data, model hyper-parameters), please contact the archive maintainer.
Evaluation on newstest2020 (BLEU):
en->pl: 12.3
pl->en: 20.0
(Evaluated using multeval: https://github.com/jhclark/multeval)
Tokenizer, POS Tagger, Lemmatizer, and Parser model based on the PDT-C 1.0 treebank (https://hdl.handle.net/11234/1-3185). The model documentation including performance can be found at https://ufal.mff.cuni.cz/udpipe/2/models#czech_pdtc1.0_model . To use these models, you need UDPipe version 2.1, which you can download from https://ufal.mff.cuni.cz/udpipe/2 .
DZ Interset is a means of converting among various tag sets in natural language processing. The core idea is similar to interlingua-based machine translation. DZ Interset defines a set of features that are encoded by the various tag sets. The set of features should be as universal as possible. It does not need to encode everything that is encoded by any tag set but it should encode all information that people may want to access and/or port from one tag set to another.
New tag sets are attached by writing a driver for them. Once the driver is ready, you can easily convert tags between the new set and any other set for which you also have a driver. This reusability is an obvious advantage over writing a targeted conversion procedure each time you need to convert between a particular pair of tag sets. and grant MSM 0021620838 of the Ministry of Education of the Czech Republic
Extremely fast digital audio channelizer implementation, usable as a building block for experimental ASR front-ends or signal denoising applications. Also applicable in software defined radios, due to its high throughput. It comes in a form of a C/C++ library and an executable example program which reads input stream, splitting it into equidistant frequency channels, emitting their data to the output.
Features:
(1) Hand tuned SIMD-aware assembly for x86 (SSE) and IA64 (AVX) as well as for ARM (NEON) processors.
(2) Generic non-SIMD C++ implementation for other architectures.
(3) Capable of taking advantage of multicore CPUs.
(4) Fully configurable number of channels and the output decimation rate.
(5) User supplied FIR of the channel separation filter, which allows to specify the width of the channels, whether they should overlap or be separated.
(6) Input and output signal samples are treated as complex numbers.
(7) Speed over 750 complex MS/s achieved on Core i7 4710HQ @ 2.5GHz, when channelizing into 72 output channels with a FIR length of 1152 samples, using 3 computing threads.
(8) Runs under Linux OS.
POS Tagger and Lemmatizer models for EvaLatin2020 data (https://github.com/CIRCSE/LT4HALA). The model documentation including performance can be found at https://ufal.mff.cuni.cz/udpipe/2/models#evalatin20_models .
To use these models, you need UDPipe version at least 2.0, which you can download from https://ufal.mff.cuni.cz/udpipe/2 .
EVALD 1.0 for Foreigners is a software for automatic evaluation of surface coherence (cohesion) in Czech texts written by non-native speakers of Czech.
EVALD 2.0 for Foreigners is a software for automatic evaluation of surface coherence (cohesion) in Czech texts written by non-native speakers of Czech.
EVALD 3.0 for Foreigners is a software for automatic evaluation of surface coherence (cohesion) in Czech texts written by non-native speakers of Czech.
EVALD 4.0 for Beginners is a software that serves for automatic evaluation of Czech texts written by non-native speakers of Czech – language beginners.
EVALD 4.0 for Foreigners is a software for automatic evaluation of surface coherence (cohesion) in Czech texts written by non-native speakers of Czech.
Fairytale Child is a simple chatbot trying to simulate a curious child. It asks the user to tell a fairy tale, often interrupting to ask for details and clarifications. However, it remembers what it was told and tries to show it if possible.
The chatbot can communicate in Czech and in English. It analyzes the morphology of each sentence produced by the user with natural language processing tools, tries to identify potential questions to ask, and then asks one. A morphological generator is employed to generate correctly inflected sentences in Czech, so that the resulting sentences sound as natural as possible.
Pohádkové dítě je jednoduchý chatbot, simulující zvídavé dítě. Požádá uživatele, aby mu vyprávěl pohádku, ale často ho přerušuje, aby se zeptal na detaily a vysvětlení. Pamatuje si ale, co mu uživatel řekl, a snaží se to pokud možno dát najevo.
Chatbot umí komunikovat česky a anglicky. Analyzuje tvarosloví každé uživatelovy věty pomocí NLP nástrojů, pokusí se nalézt chodnou otázku, a tu pak položí. Aby tvořené české věty zněly co nejpřirozeněji, využívá se pro skloňování tvaroslovný generátor. and The work has been supported by GAUK 1572314 and SVV 260104.
It has been using language resources developed, stored and distributed by the LINDAT/CLARIN project of the Ministry of Education, Youth and Sports of the Czech Republic (project LM2010013).
Fairytale Child is a simple chatbot trying to simulate a curious child. It asks the user to tell a fairy tale, often interrupting to ask for details and clarifications. However, it remembers what it was told and tries to show it if possible.
The chatbot can communicate in Czech and in English. It analyzes the morphology of each sentence produced by the user with natural language processing tools, tries to identify potential questions to ask, and then asks one. A morphological generator is employed to generate correctly inflected sentences in Czech, so that the resulting sentences sound as natural as possible.
Pohádkové dítě je jednoduchý chatbot, simulující zvídavé dítě. Požádá uživatele, aby mu vyprávěl pohádku, ale často ho přerušuje, aby se zeptal na detaily a vysvětlení. Pamatuje si ale, co mu uživatel řekl, a snaží se to pokud možno dát najevo.
Chatbot umí komunikovat česky a anglicky. Analyzuje tvarosloví každé uživatelovy věty pomocí NLP nástrojů, pokusí se nalézt chodnou otázku, a tu pak položí. Aby tvořené české věty zněly co nejpřirozeněji, využívá se pro skloňování tvaroslovný generátor. and The work has been supported by GAUK 1572314 and SVV 260104.
It has been using language resources developed, stored and distributed by the LINDAT/CLARIN project of the Ministry of Education, Youth and Sports of the Czech Republic (project LM2010013).
Fairytale Child is a simple chatbot trying to simulate a curious child. It asks the user to tell a fairy tale, often interrupting to ask for details and clarifications. However, it remembers what it was told and tries to show it if possible.
The chatbot can communicate in Czech and in English. It analyzes the morphology of each sentence produced by the user with natural language processing tools, tries to identify potential questions to ask, and then asks one. A morphological generator is employed to generate correctly inflected sentences in Czech, so that the resulting sentences sound as natural as possible.
Pohádkové dítě je jednoduchý chatbot, simulující zvídavé dítě. Požádá uživatele, aby mu vyprávěl pohádku, ale často ho přerušuje, aby se zeptal na detaily a vysvětlení. Pamatuje si ale, co mu uživatel řekl, a snaží se to pokud možno dát najevo.
Chatbot umí komunikovat česky a anglicky. Analyzuje tvarosloví každé uživatelovy věty pomocí NLP nástrojů, pokusí se nalézt chodnou otázku, a tu pak položí. Aby tvořené české věty zněly co nejpřirozeněji, využívá se pro skloňování tvaroslovný generátor. and The work has been supported by GAUK 1572314 and SVV 260104.
It has been using language resources developed, stored and distributed by the LINDAT/CLARIN project of the Ministry of Education, Youth and Sports of the Czech Republic (project LM2010013).
Fairytale Child is a simple chatbot trying to simulate a curious child. It asks the user to tell a fairy tale, often interrupting to ask for details and clarifications. However, it remembers what it was told and tries to show it if possible.
The chatbot can communicate in Czech and in English. It analyzes the morphology of each sentence produced by the user with natural language processing tools, tries to identify potential questions to ask, and then asks one. A morphological generator is employed to generate correctly inflected sentences in Czech, so that the resulting sentences sound as natural as possible.
Pohádkové dítě je jednoduchý chatbot, simulující zvídavé dítě. Požádá uživatele, aby mu vyprávěl pohádku, ale často ho přerušuje, aby se zeptal na detaily a vysvětlení. Pamatuje si ale, co mu uživatel řekl, a snaží se to pokud možno dát najevo.
Chatbot umí komunikovat česky a anglicky. Analyzuje tvarosloví každé uživatelovy věty pomocí NLP nástrojů, pokusí se nalézt chodnou otázku, a tu pak položí. Aby tvořené české věty zněly co nejpřirozeněji, využívá se pro skloňování tvaroslovný generátor. and The work has been supported by GAUK 1572314 and SVV 260104.
It has been using language resources developed, stored and distributed by the LINDAT/CLARIN project of the Ministry of Education, Youth and Sports of the Czech Republic (project LM2010013).
Environmental impact assessment (EIA) is the formal process used to predict the environmental consequences of a plan. We present a rule-based extraction system to mine Czech EIA documents. The extraction rules work with a set of documents enriched with morphological information and manually created vocabularies of terms supposed to be extracted from the documents, e.g. basic information about the project (address, ID company, ...), data on the impacts and outcomes (waste substances, endangered species, ...), a final opinion. The documents Notice of Intent contains the section BI2 with the information on the scope (capacity) of the plan.
jusText is a heuristic based boilerplate removal tool useful for cleaning documents in large textual corpora. The tool has been implemented in Python, licensed under New BSD License and made an open source software (available for download including the source code at http://code.google.com/p/justext/). It is successfully used for cleaning large textual corpora at Natural language processing centre at Faculty of informatics, Masaryk university Brno and it's industry partners. The research leading to this piece of software was published in author's Ph.D. thesis "Removing Boilerplate and Duplicate Content from Web Corpora". The boilerplate removal algorithm is able to remove most of non-grammatical sentences from a web page like navigation, advertisements, tables, short notes and so on. It has been shown it overperforms or at least keeps up with it's competitors (according to comparison with participants of Cleaneval competition in author's Ph.D. thesis). The precise removal of unwanted content and scalability of the algorithm has been demonstrated while building corpora of American Spanish, Arabic, Czech, French, Japanese, Russian, Tajik, and six Turkic languages consisting --- over 20 TB of HTML pages were processed resulting in corpora of 70 billions tokens altogether. and PRESEMT, Lexical Computing Ltd
This editor was developed especially for the needs of the KAMOKO project (https://lindat.mff.cuni.cz/repository/xmlui/handle/11372/LRT-3261). The editor allows the quick entry of example sentences and sentence variants as well as the corresponding speaker ratings.
An interactive web demo for querying selected ÚFAL and LINDAT corpora. LINDAT/CLARIN KonText is a fork of ÚČNK KonText (https://github.com/czcorpus/kontext, maintained by Tomáš Machálek) that contains some modifications and additional features. Kontext, in turn, is a fork of the Bonito 2.68 python web interface to the corpus management tool Manatee (http://nlp.fi.muni.cz/trac/noske, created by Pavel Rychlý).
Statistical spell- and (occasional) grammar-checker. There are three versions: a unix command line utility and an OS X SpellServer with a System Service, that integrates with native OS X GUI applications, and a web service run by Lindat-Clarin, that can be used either through a web form in a browser, or by web applications using API. and The LINDAT-CLARIN project (LM2010013), fully supported by TheMinistry of Education, Sports and Youth of The Czech Republic under the programme LM of "Large Infrastructures"
Korektor is a statistical spell-checker and (occasionally) grammar-checker. It is released under 2-Clause BSD license http://opensource.org/licenses/BSD-2-Clause.
Korektor started with Michal Richter's diploma thesis Advanced Czech Spellchecker https://redmine.ms.mff.cuni.cz/documents/1, but it is being developed further. There are two versions: a command line utility (tested on Linux, Windows and OS X) and a REST service with publicly available API http://lindat.mff.cuni.cz/services/korektor/api-reference.php and HTML front end https://lindat.mff.cuni.cz/services/korektor/.
Lingua::Interset is a universal morphosyntactic feature set to which all tagsets of all corpora/languages can be mapped. Version 2.026 covers 37 different tagsets of 21 languages. Limited support of the older drivers for other languages (which are not included in this package but are available for download elsewhere) is also available; these will be fully ported to Interset 2 in future.
Interset is implemented as Perl libraries. It is also available via CPAN.
This toolkit comprises the tools and supporting scripts for unsupervised induction of dependency trees from raw texts or texts with already assigned part-of-speech tags. There are also scripts for simple machine translation based on unsupervised parsing and scripts for minimally supervised parsing into Universal-Dependencies style.
Source code of the first full and running version for the Malach Center User Interface, does not contain data or metadata fo the digital objects and resources.
En-De translation models, exported via TensorFlow Serving, available in the Lindat translation service (https://lindat.mff.cuni.cz/services/translation/).
The models were trained using the MCSQ social surveys dataset (available at https://repo.clarino.uib.no/xmlui/bitstream/handle/11509/142/mcsq_v3.zip).
Their main use should be in-domain translation of social surveys.
Models are compatible with Tensor2tensor version 1.6.6.
For details about the model training (data, model hyper-parameters), please contact the archive maintainer.
Evaluation on MCSQ test set (BLEU):
en->de: 67.5 (train: genuine in-domain MCSQ data only)
de->en: 75.0 (train: additional in-domain backtranslated MCSQ data)
(Evaluated using multeval: https://github.com/jhclark/multeval)
En-Ru translation models, exported via TensorFlow Serving, available in the Lindat translation service (https://lindat.mff.cuni.cz/services/translation/).
The models were trained using the MCSQ social surveys dataset (available at https://repo.clarino.uib.no/xmlui/bitstream/handle/11509/142/mcsq_v3.zip).
Their main use should be in-domain translation of social surveys.
Models are compatible with Tensor2tensor version 1.6.6.
For details about the model training (data, model hyper-parameters), please contact the archive maintainer.
Evaluation on MCSQ test set (BLEU):
en->ru: 64.3 (train: genuine in-domain MCSQ data)
ru->en: 74.7 (train: additional backtranslated in-domain MCSQ data)
(Evaluated using multeval: https://github.com/jhclark/multeval)
MorphoDiTa: Morphological Dictionary and Tagger is an open-source tool for morphological analysis of natural language texts. It performs morphological analysis, morphological generation, tagging and tokenization and is distributed as a standalone tool or a library, along with trained linguistic models. In the Czech language, MorphoDiTa achieves state-of-the-art results with a throughput around 10-200K words per second. MorphoDiTa is a free software under LGPL license and the linguistic models are free for non-commercial use and distributed under CC BY-NC-SA license, although for some models the original data used to create the model may impose additional licensing conditions.
This tool is the first morphological analyzer ever for this language.
The analyzer is a FST that produces all possible segmentations and tagging sequences in a word-by-word fashion.
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).
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/). and 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.
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/). and 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.
MUSCIMarker is an open-source tool for annotating visual objects and their relationships in binary images. It is implemented in Python, known to run on Windows, Linux and OS X, and supports working offline. MUSCIMarker is being used for creating a dataset of musical notation symbols, but can support any object set.
The user documentation online is currently (12.2016) incomplete, as it is continually changing to reflect annotators' comments and incorporate new features. This version of the software is *not* the final one, and it is under continuous development (we're currently working on adding grayscale image support with auto-binarization, and Android support for touch-based annotation). However, the current version (1.1) has already been used to annotate more than 100 pages of sheet music, over all the major desktop OSes, and I believe it is already in a state where it can be useful beyond my immediate music notation data gathering use case.
NameTag is an open-source tool for named entity recognition (NER). NameTag identifies proper names in text and classifies them into predefined categories, such as names of persons, locations, organizations, etc. NameTag is distributed as a standalone tool or a library, along with trained linguistic models. In the Czech language, NameTag achieves state-of-the-art performance (Straková et al. 2013). NameTag is a free software under LGPL license and the linguistic models are free for non-commercial use and distributed under CC BY-NC-SA license, although for some models the original data used to create the model may impose additional licensing conditions.
NameTag 2 is a named entity recognition tool. It recognizes named entities (e.g., names, locations, etc.) and can recognize both flat and embedded (nested) entities. NameTag 2 can be used either as a commandline tool or by requesting the NameTag webservice.
NameTag webservice can be found at:
https://lindat.mff.cuni.cz/services/nametag/
NameTag commandline tool can be downloaded from NameTag GitHub repository, branch nametag2:
git clone https://github.com/ufal/nametag -b nametag2
Latest models and documentation can be found at:
https://ufal.mff.cuni.cz/nametag/2
This software subject to the terms of the Mozilla Public License, v. 2.0 (http://mozilla.org/MPL/2.0/). The associated models are distributed under CC BY-NC-SA license.
Please cite as:
Jana Straková, Milan Straka, Jan Hajič (2019): Neural Architectures for Nested NER through Linearization. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 5326-5331, Association for Computational Linguistics, Stroudsburg, PA, USA, ISBN 978-1-950737-48-2 (https://aclweb.org/anthology/papers/P/P19/P19-1527/)
onion (ONe Instance ONly) is a tool for removing duplicate parts from large collections of texts. The tool has been implemented in Python, licensed under New BSD License and made an open source software (available for download including the source code at http://code.google.com/p/onion/). It is being successfuly used for cleaning large textual corpora at Natural language processing centre at Faculty of informatics, Masaryk university Brno and it's industry partners. The research leading to this piece of software was published in author's Ph.D. thesis "Removing Boilerplate and Duplicate Content from Web Corpora". The deduplication algorithm is based on comparing n-grams of words of text. The author's algorithm has been shown to be more suitable for textual corpora deduplication than competing algorithms (Broder, Charikar): in addition to detection of identical or very similar (95 %) duplicates, it is able to detect even partially similar duplicates (50 %) still achieving great performace (further described in author's Ph.D. thesis). The unique deduplication capabilities and scalability of the algorithm were been demonstrated while building corpora of American Spanish, Arabic, Czech, French, Japanese, Russian, Tajik, and six Turkic languages consisting --- several TB of text documents were deduplicated resulting in corpora of 70 billions tokens altogether. and PRESEMT, Lexical Computing Ltd
Omorfi is free and open source project containing various tools and data for handling Finnish texts in a linguistically motivated manner. The main components of this repository are:
1) a lexical database containing hundreds of thousands of words (c.f. lexical statistics),
2) a collection of scripts to convert lexical database into formats used by upstream NLP tools (c.f. lexical processing),
3) an autotools setup to build and install (or package, or deploy): the scripts, the database, and simple APIs / convenience processing tools, and
4) a collection of relatively simple APIs for a selection of languages and scripts to apply the NLP tools and access the database
Parsito is a fast open-source dependency parser written in C++. Parsito is based on greedy transition-based parsing, it has very high accuracy and achieves a throughput of 30K words per second. Parsito can be trained on any input data without feature engineering, because it utilizes artificial neural network classifier. Trained models for all treebanks from Universal Dependencies project are available (37 treebanks as of Dec 2015).
Parsito is a free software under Mozilla Public License 2.0 (http://www.mozilla.org/MPL/2.0/) and the linguistic models are free for non-commercial use and distributed under CC BY-NC-SA (http://creativecommons.org/licenses/by-nc-sa/4.0/) license, although for some models the original data used to create the model may impose additional licensing conditions.
Parsito website http://ufal.mff.cuni.cz/parsito contains download links of both
the released packages and trained models, hosts documentation and offers online
demo.
Parsito development repository http://github.com/ufal/parsito is hosted on
GitHub.
System for querying annotated treebanks in PML format. The querying uses it own query language with graphical representation. It has two different implementations (SQL and Perl) and several clients (TrEd, browser-based, command line interface).
The presented game is designed to teach the six most frequent English prepositions (to, of, in, for, on, and with) at the A1 to A2 levels of proficiency. Prep for Adventure is a single-player game comprised of five separate tasks – jumping puzzle, cooking, town maze, lighting the goblets, and a banter with a classmate. Their mechanics are then combined in the final task (The Final Fight) to elicit the correct responses of the subject.
The language used in the game is adjusted for the subjects’ level of proficiency, the game is fully voiced and offers a degree of customization. All tasks are based on the gap-filling type of exercise where subjects have to complete a sentence with a missing word, either by typing it in or via different kinds of multiple-choice formats. The game is designed to advance the subjects’ performance in prepositional structures by exposing players to as much input as possible.
The length of one average playthrough is approximately 30-45 minutes. The game was created in the RPG Maker MV engine where RPG stands for role-playing game, which is a genre of a game in which the player adopts a role/roles of a fictional character/characters in a (partly or fully) invented setting.
The game story:
The Grammar School of Witchcraft has been taken over by the Evil Preposition Magician and the player is trying to win their school back alongside with a young witch named Morphologina (the player’s guide).
The SynSemClass Search Tool provides a web search tool for the SynSemClass 5.0 ontology. It includes several search options and criteria for building complex queries. The search results are rendered in a clear and user-friendly interactive representation.
This submission contains Dockerfile for creating a Docker image with compiled Tensor2tensor backend with compatible (TensorFlow Serving) models available in the Lindat Translation service (https://lindat.mff.cuni.cz/services/transformer/). Additionally, the submission contains a web frontend for simple in-browser access to the dockerized backend service.
Tensor2Tensor (https://github.com/tensorflow/tensor2tensor) is a library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
A simple way of browsing CoNLL format files in your terminal. Fast and text-based.
To open a CoNLL file, simply run: ./view_conll sample.conll
The output is piped through less, so you can use less commands to navigate the
file; by default the less searches for sentence beginnings, so you can use "n"
to go to next sentence and "N" to go to previous sentence. Close by "q". Trees
with a high number of non-projective edges may be difficult to read, as I have
not found a good way of displaying them intelligibly.
If you are on Windows and don't have less (but have Python), run like this: python view_conll.py sample.conll
For complete instructions, see the README file.
You need Python 2 to run the viewer.
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").
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".
En-De translation models, exported via TensorFlow Serving, available in the Lindat translation service (https://lindat.mff.cuni.cz/services/translation/).
Models are compatible with Tensor2tensor version 1.6.6.
For details about the model training (data, model hyper-parameters), please contact the archive maintainer.
Evaluation on newstest2020 (BLEU):
en->de: 25.9
de->en: 33.4
(Evaluated using multeval: https://github.com/jhclark/multeval)
En-Ru translation models, exported via TensorFlow Serving, available in the Lindat translation service (https://lindat.mff.cuni.cz/services/translation/).
Models are compatible with Tensor2tensor version 1.6.6.
For details about the model training (data, model hyper-parameters), please contact the archive maintainer.
Evaluation on newstest2020 (BLEU):
en->ru: 18.0
ru->en: 30.4
(Evaluated using multeval: https://github.com/jhclark/multeval)
TXM is a free and open-source cross-platform Unicode & XML based text/corpus analysis environment and graphical client, supporting Windows, Linux and Mac OS X. It can also be used online as a J2EE standard compliant web portal (GWT based) with access control built in.
Pretrained model weights for the UDify model, and extracted BERT weights in pytorch-transformers format. Note that these weights slightly differ from those used in the paper.
UDPipe is an trainable pipeline for tokenization, tagging, lemmatization and dependency parsing of CoNLL-U files. UDPipe is language-agnostic and can be trained given only annotated data in CoNLL-U format. Trained models are provided for nearly all UD treebanks. UDPipe is available as a binary, as a library for C++, Python, Perl, Java, C#, and as a web service.
UDPipe is a free software under Mozilla Public License 2.0 (http://www.mozilla.org/MPL/2.0/) and the linguistic models are free for non-commercial use and distributed under CC BY-NC-SA (http://creativecommons.org/licenses/by-nc-sa/4.0/) license, although for some models the original data used to create the model may impose additional licensing conditions. UDPipe is versioned using Semantic Versioning (http://semver.org/).
UDPipe website http://ufal.mff.cuni.cz/udpipe contains download links of both the released packages and trained models, hosts documentation and offers online demo.
UDPipe development repository http://github.com/ufal/udpipe is hosted on GitHub.
UDPipe 2 is a POS tagger, lemmatizer and dependency parser.
Compared to UDPipe 1:
- UDPipe 2 is Python-only and tested only in Linux,
- UDPipe 2 is meant as a research tool, not as a user-friendly UDPipe 1 replacement,
- UDPipe 2 achieves much better performance, but requires a GPU for reasonable performance,
- UDPipe 2 does not perform tokenization by itself – it uses UDPipe 1 for that.
UDPipe 2 is available in the udpipe-2 branch of the UDPipe repository at https://github.com/ufal/udpipe/tree/udpipe-2. It is a free software under Mozilla Public License 2.0 (http://www.mozilla.org/MPL/2.0/) and the models are free for non-commercial use and distributed under CC BY-NC-SA (http://creativecommons.org/licenses/by-nc-sa/4.0/) license, although for some models the original data used to create the model may impose additional licensing conditions.
UDPipe 2 is also available as a REST service running at https://lindat.mff.cuni.cz/services/udpipe. If you like, you can use the https://github.com/ufal/udpipe/blob/udpipe-2/udpipe2_client.py script to interact with it.
Parsing models for all Universal Depenencies 1.2 Treebanks, created solely using UD 1.2 data (http://hdl.handle.net/11234/1-1548).
To use these models, you need Parsito binary, which you can download from http://hdl.handle.net/11234/1-1584.
Tokenizer, POS Tagger, Lemmatizer and Parser models for all Universal Depenencies 1.2 Treebanks, created solely using UD 1.2 data (http://hdl.handle.net/11234/1-1548).
To use these models, you need UDPipe binary, which you can download from http://ufal.mff.cuni.cz/udpipe.
Tokenizer, POS Tagger, Lemmatizer and Parser models for all 50 languages of Universal Depenencies 2.0 Treebanks, created solely using UD 2.0 data (http://hdl.handle.net/11234/1-1983). The model documentation including performance can be found at http://ufal.mff.cuni.cz/udpipe/users-manual#universal_dependencies_20_models .
To use these models, you need UDPipe binary version at least 1.2, which you can download from http://ufal.mff.cuni.cz/udpipe .
In addition to models itself, all additional data and value of hyperparameters used for training are available in the second archive, allowing reproducible training.
Tokenizer, POS Tagger, Lemmatizer and Parser models for 123 treebanks of 69 languages of Universal Depenencies 2.10 Treebanks, created solely using UD 2.10 data (https://hdl.handle.net/11234/1-4758). The model documentation including performance can be found at https://ufal.mff.cuni.cz/udpipe/2/models#universal_dependencies_210_models .
To use these models, you need UDPipe version 2.0, which you can download from https://ufal.mff.cuni.cz/udpipe/2 .
Tokenizer, POS Tagger, Lemmatizer and Parser models for 131 treebanks of 72 languages of Universal Depenencies 2.12 Treebanks, created solely using UD 2.12 data (https://hdl.handle.net/11234/1-5150). The model documentation including performance can be found at https://ufal.mff.cuni.cz/udpipe/2/models#universal_dependencies_212_models .
To use these models, you need UDPipe version 2.0, which you can download from https://ufal.mff.cuni.cz/udpipe/2 .
Tokenizer, POS Tagger, Lemmatizer and Parser models for 84 treebanks of 56 languages of Universal Depenencies 2.3 Treebanks, created solely using UD 2.3 data (http://hdl.handle.net/11234/1-2895). The model documentation including performance can be found at http://ufal.mff.cuni.cz/udpipe/models#universal_dependencies_23_models .
To use these models, you need UDPipe binary version at least 1.2, which you can download from http://ufal.mff.cuni.cz/udpipe .
In addition to models itself, all additional data and value of hyperparameters used for training are available in the second archive, allowing reproducible training.
Tokenizer, POS Tagger, Lemmatizer and Parser models for 90 treebanks of 60 languages of Universal Depenencies 2.4 Treebanks, created solely using UD 2.4 data (http://hdl.handle.net/11234/1-2988). The model documentation including performance can be found at http://ufal.mff.cuni.cz/udpipe/models#universal_dependencies_24_models .
To use these models, you need UDPipe binary version at least 1.2, which you can download from http://ufal.mff.cuni.cz/udpipe .
In addition to models itself, all additional data and value of hyperparameters used for training are available in the second archive, allowing reproducible training.
Tokenizer, POS Tagger, Lemmatizer and Parser models for 94 treebanks of 61 languages of Universal Depenencies 2.5 Treebanks, created solely using UD 2.5 data (http://hdl.handle.net/11234/1-3105). The model documentation including performance can be found at http://ufal.mff.cuni.cz/udpipe/models#universal_dependencies_25_models .
To use these models, you need UDPipe binary version at least 1.2, which you can download from http://ufal.mff.cuni.cz/udpipe .
In addition to models itself, all additional data and value of hyperparameters used for training are available in the second archive, allowing reproducible training.
Tokenizer, POS Tagger, Lemmatizer and Parser models for 99 treebanks of 63 languages of Universal Depenencies 2.6 Treebanks, created solely using UD 2.6 data (https://hdl.handle.net/11234/1-3226). The model documentation including performance can be found at https://ufal.mff.cuni.cz/udpipe/2/models#universal_dependencies_26_models .
To use these models, you need UDPipe version 2.0, which you can download from https://ufal.mff.cuni.cz/udpipe/2 .
This program enables the user to visualize f0 contours, to plot vowels in the F1/F2 space for multiple points in the vowel interval, e.g. at 20%, 50% and 80%, and to visualize vowel durations.
(The tool is implemented in R. We used the following packages: phonR, gplots, plotrix, lattice, readxl, WriteXLS, DT,
psych and pracma. We thank the developers of these packages.)
Vystadial 2013 is a dataset of telephone conversations in English and Czech, developed for training acoustic models for automatic speech recognition in spoken dialogue systems. It ships in three parts: Czech data, English data, and scripts.
The data comprise over 41 hours of speech in English and over 15 hours in Czech, plus orthographic transcriptions. The scripts implement data pre-processing and building acoustic models using the HTK and Kaldi toolkits.
This is the scripts part of the dataset. and This research was funded by the Ministry of
Education, Youth and Sports of the Czech Republic under the grant agreement
LK11221.