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.