Icelandic Resources

From Icelandic Parsed Historical Corpus (IcePaHC)
Jump to: navigation, search

IceNLP is a set of free and open source tools (LGPL) to process Icelandic text. It includes a part-of-speech tagger, a shallow parser and a lemmatizer. It also contains some extra tools such as segmentizers (sentence tokenizer), one based on the SRX standard and one developed specifically for IceNLP.