Service integrates several keyword determination methods, including generative models and multi-label classification. The combination of several advanced techniques makes the results more reliable and accurate.
A portal that implements a transcription chain for batch processing of speech files using automatic speech recognition, the OCTRA editor, the Munich Automatic Segmentation MAUS and the EMU-webApp viewer.
Service that is used to process literary texts to extract statistical information from them. The service allows, among others, lemmatization, determining parts of speech, characterization of verbs used in the text, creating a list of proper names and extracting statistics from the corpus of texts.
Set of tools used in natural language processing to assign labels or tags to text elements such as words or tokens. Postagger works at the stage after the text has been analyzed by a morphological or syntactic tagger and is intended to make the final classification and assign appropriate labels to individual text elements.
Based on a deep language model that analyzes the semantic content of statements and generates texts with the same meaning but with a changed form. The tool returns text of a similar length to the text entered by the user.
The LiLa Text Linker is a pos-tagger and Lemmatizer for Latin that also provides, for each analyzed token, a link to the lemma entry in the LOD-compliant LiLa Lemma Bank. The tool was produced in the context of the 'LiLa - Linking Latin' project (https://lila-erc.eu/).