swe-msd-hunpos-suc3-1800

Sentence segments are analysed to enrich tokens with part-of-speech tags and morphosyntactic information. In addition to the pos model inflection lists are provided to Hunpos to make more accuare part-of-speech predictions for Swedish from the 1800's.

This analysis is used with Sparv. Check out Sparv's quick start guide to get started!

To use this analysis, add the following line under export.annotations in the Sparv corpus configuration file:

- <token>:hunpos.msd  # Part-of-speeches with morphological descriptions

In order to use this annotation you need to add the following setting to your Sparv corpus configuration file:

metadata:
  language: swe
  variety: "1800"

For more info on how to use Sparv, check out the Sparv documentation.

Example output:

<token msd="NN.UTR.SIN.DEF.NOM">Lådan</token>
<token msd="VB.PRT.AKT">var</token>
<token msd="PC.PRF.UTR.SIN.IND.NOM">upphängd</token>
<token msd="PP">under</token>
<token msd="DT.UTR.SIN.DEF">den</token>
<token msd="NN.UTR.SIN.IND.NOM">waggon</token>
<token msd="HA">hvari</token>
<token msd="DT.UTR+NEU.PLU.DEF">de</token>
<token msd="JJ.POS.UTR+NEU.PLU.IND+DEF.NOM">andra</token>
<token msd="NN.NEU.PLU.DEF.NOM">djuren</token>
<token msd="VB.INF.AKT">befunno</token>
<token msd="PN.UTR+NEU.SIN+PLU.DEF.OBJ">sig</token>
<token msd="MAD">.</token>