MaltParser

Swedish MaltParser model

The file swemalt-1.7.2.mco contains a single malt configuration for parsing Swedish text with MaltParser, version 1.7.2. The parsing model has been trained on the Talbanken section of the Swedish Treebank. The parser presupposes that the input is in CoNLL format and tagged with the SUC part-of-speech tags and morphosyntactic features as shown in the example below. (For more information about the part-of-speech tags and morphosyntactic features, see the documentation of the Swedish Treebank.)

Running swemalt

Download swemalt-1.7.2.mco into your working directory and execute the following command:

prompt> $ java -Xmx1024m -jar maltparser-1.7.2.jar -c swemalt-1.7.2 -i infile.conll -o outfile.conll -m parse

where infile.conll and outfile.conll should be replaced by the names of your input and output files. For more information, see the MaltParser user guide.

Here is an example of an input sentence:

1	För	_	PP	PP	_	
2	telefonrådfrågning	_	NN	NN	UTR|SIN|IND|NOM	
3	betalar	_	VB	VB	PRS|AKT	
4	försäkringskassan	_	NN	NN	UTR|SIN|DEF|NOM	
5	4	_	RG	RG	NOM
6	kronor	_	NN	NN	UTR|PLU|IND|NOM
7	till	_	PP	PP	_
8	sjukvårdshuvudmannen	_	NN	NN	UTR|SIN|DEF|NOM
9	.	_	MAD	MAD	_

Note that the columns are tab-separate and that columns 4 and 5 should have the same value.