General | Example visualisations

UDPipe - General | udpipe the R package | UDPipe the C++ library | udpipe models | Pre-trained models | Build your own annotator models | Annotate text | Load the model | Annotate your text | Tokenisation, tagging and parsing | Only part of the annotation | My text data is already tokenised | Remarks | Support in text mining

GitHub - package repository | BNOSAC

udpipe universe

UDPipe - Basic Analytics | Start with annotating | Basic frequency statistics | Finding keywords | Co-occurrences | Nouns / adjectives used in same sentence | Nouns / adjectives which follow one another | Correlations | Support in text mining

General | Model building | Basic example | Providing more details on the model annotation process | Settings for the tokenizer: | Settings for the tagger: | Settings for the dependency parser: | Example | Example on UD 2.6 on German GSD | Support in text mining

Parallel Annotation | When to run in parallel? | Using other packages allowing parallel computation

UDPipe for Topic Modelling | Start with annotating | Basic topic modelling | Topic modelling only on specific POS tags | Predict new documents | Interpret topics | Doing the same on the adjectives + nouns | Topic visualisation | Include keywords in topic models | Other option to build document term matricis | Summarising topics | Support in text mining

Example | Support in big data and Spark analysis

Textrank | Identify relevant sentences | Identify relevant keywords | Example text | Textrank for keyword extraction | Textrank for sentence ranking | Define sentences and terminology | Applying textrank_sentences | Minhash | Support in text mining

Example | A small note on encodings

Smith Waterman | Example usage | Example matching 2 names | Example matching 2 translations | Find relevant sequences of texts in other texts | Get alignment overview as a data.frame

GitHub - package repository | BNOSAC