Analyses

Dependency parsing with Stanza's standard model for English

Stanza-based morphological analysis for English, using universal features (UD)

Part-of-speech annotation with Penn Treebank tags with Stanza's standard model for English

Sentence segmentation with Stanza's standard model for English

Segments text into paragraphs by blank lines using the RegexpTokenizer from NLTK

Segments text into paragraphs by whitespaces using the RegexpTokenizer from NLTK

Segments text into sentences by linebreaks using the RegexpTokenizer from NLTK

Segments text into sentences by whitespaces using the RegexpTokenizer from NLTK

Tokenizes text into tokens by linebreaks using the RegexpTokenizer from NLTK

Analysis of SALDO lemgram compounds including a probability ranking

Swedish dependency parsing from MaltParser trained on Sweedish treebank

Export of corpus data in Språkbanken Text's CoNLL-U format

Annotate text chunks with location data, based on metadata containing location names

Full-form lookup for SALDO citation forms (lemmas)

Swedish citation form analysis (base forms, lemmas) by Stanza, trained on SUC3

Lexical classes from SweFN on text-level

Lexical classes from SweFN on token-level

Annotation of morphological features (SUC) by Hunpos for Swedish

Annotation of morphological features (SUC) by Stanza for Swedish

Named entity recognition (NER) recognises named entities such as locations, persons and time expressions in text.

Swedish part-of-speech annotation with SUC tags by Hunpos

Swedish part-of-speech annotation with SUC tags by Stanza

Annotation of Swedish texts with nominal ratios which indicate the difficulty of the texts

Word sense disambiguation based on SALDO annotation

Segments text into sentences, custom-made for Swedish

Collection of Sparv analyses for modern Swedish

XML corpus export preserving whitespaces from source file

XML corpus export with scrambled contents

Word prediction annotations for each word in a text.