Before using the service, please read the preliminary information containing a description of steps that enable access to the CLARIN-PL developer interface.
TxTParaphrase allows you to paraphrase short texts.
The service is based on a deep model t5-utterance-rewriting-v2-plt5-large. It divides the text into smaller fragments of n_words length, processes them, and then combines the results.
The service can be run by using an LPMN query in the LPMN Client service:
type - model selection, for example t5-utterance-rewriting-v2-plt5-largen_words - selection of the character limit for the fragments that the input text is to be divided into, for example 400 charactersThe service can be run in the Windows system with default values using the following LPMN query: ['any2txt',{'txt2txt':{'type':'t5-utterance-rewriting-v2-plt5-large','n_words':'400'}}]
[['any2txt',{'txt2txt':{'type':'t5-utterance-rewriting-v2-plt5-large','n_words':'400'}}]] - input data in the form of a compressed directory (.zip)
Text, a text file or .zip archive.
Text, a text file or .zip archive.
In Colab: TxTParaphrase - Paraphrasing of short texts
(C) CLARIN-PL