Zdeněk Kasner
Zdeněk Kasner
The user will be able to interactively generate output with their own model. If the model is loaded alongside the app (which is the default idea), it should be fairly...
Currently, only a very basic version of the interactive mode is implemented (#4). The user can enter edit mode, change cell value(s), and re-run the pipelines. Only the edited cell...
Add some basic assertions, e.g.: - all the examples in the dataset may be transformed into a table - all the tables are rectangular (cf. #17) - all the examples...
For a particular dataset split, the user will upload a text file. The file will have as many lines as the number of examples in the dataset. Each line will...
Add other methods to generate text from the table except for a seq2seq model. The methods may include: - represeting cells as text using simple templates, - deriving information from...
Diacritics in names of the authors may be incorrect on DBLP (see e.g. https://dblp.org/rec/conf/inlg/DusekK20). Can we somehow keep the entries where the diacritics is correct, or fetch the names of...
Add our open-source framework for token-level annotations of texts generated by LLMs. The framework can elicit annotations both from human crowdworkers and LLM-based evaluators.