Skip to main content
Språkbanken Text is a department within Språkbanken.

swe-lexical_classes_token-sparv-blingbring

Citation Information

Språkbanken Text (2017). swe-lexical_classes_token-sparv-blingbring (updated: 2017-09-21). [Analysis]. Språkbanken Text.
Lexical classes from Blingbring on token-level

Tokens are looked up in Blingbring in order to enrich them with information about their lexical classes.

Blingbring (version 0.2) is based on the content of Bring's Svenskt ordförråd ordnat i begreppsklasser [The Swedish vocabulary arranged into conceptual classes] (1930). The entries in Blingbring have been linked to the corresponding SALDO word sense entries. The linkages are ambiguous in many cases, but disambiguation is planned for future versions of Blingbring.

Example

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>:lexical_classes.blingbring  # Lexical classes for tokens from Blingbring

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

Example output:

<token blingbring="|">Rödräv</token>
<token blingbring="|">eller</token>
<token blingbring="|allmännelighet|antaglighet|betydelselöshet|enhetlighet|enkelhet|medelmåttighet|upprepning|uttryckslöshet|vana|vanlighet|överensstämmelse|">vanlig</token>
<token blingbring="|brunt|djur|rött|slughet|">räv</token>
<token blingbring="|förtid|långvarighet|varaktighet|">är</token>
<token blingbring="|">ett</token>
<token blingbring="|">hunddjur</token>
<token blingbring="|">och</token>
<token blingbring="|">den</token>
<token blingbring="|allmännelighet|betydenhet|flerhet|jämförelse|mängd|upprepning|vanlighet|">mest</token>
<token blingbring="|">förekommande</token>
<token blingbring="|benämning|klass|tillstånd|">arten</token>
<token blingbring="|">i</token>
<token blingbring="|">rävsläktet</token>
<token blingbring="|">.</token>

Type

  • Analysis

Task

lexical classes

Unit

token

Tool

Sparv

Tagset

Trained on

Reference corpora for relative frequencies: Göteborgsposten 2008, SUC 3.0, Bonniersromaner I (1976–77)

Created

2017-09-05

Updated

2017-09-21

Contact

Språkbanken Text
sb-info@svenska.gu.se