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".
The Thesaurus linguae Latinae is the first comprehensive dictionary of ancient Latin;
• it is compiled on the basis of all Latin texts surviving from antiquity (until AD 600), both literary and non-literary
• for less common words it cites every attestation, for the rest (those marked with an asterisk) an instructive and representative sample
• it records all meanings (including technical usages) and all constructions
• it documents peculiarities of inflection, spelling, and prosody
• it supplies information about the etymology of the Latin words and their survival in the Romance languages, contributed by recognised authorities in the fields of Indo-European and Romance studies
• it collects the comments of ancient sources on the word in question
The Thesaurus therefore offers for every Latin word a comprehensive, richly documented picture of its possibilities and history – not only for Latin scholars, but also for scholars of the various branches of ancient studies and for related disciplines.
An elegantly simple and robust machine-learning method, based on the combination of ideas from a number of MBL implementations, resulting in a useful tool for NLP research.