Lexalytics - Part of Speech (Tagging Model)

Data Mining Tool 2

About

In the provided Salience Demo app, you can run a piece of text and use the “View Chunk Tagged Text” to see the parts of speech Salience has assigned.

  • NNP: proper nouns
  • JJS: superlative adjective
  • JJ: regular adjective.

Customization

You can force parts of speech on certain words via a file called gluepatterns.dat.

  • create a gluepatterns.dat in user\tagger.
  • Taking our Best Buy example a little further, we put this line in gluepatterns.dat:
<(='Best')> (='Buy')=>NNP
(='Best') <(='Buy')>=>NNP

This tells Salience to “glue” all instances of Best Buy together and tag both words as NNP, which is a proper noun.

Documentation / Reference





Discover More
Data Mining Tool 2
Lexalytics - Entity extraction

Entity Extraction in Lexalytics To recognizes company names. Salience is looking for words or phrases that fit certain part of speech patterns. At the lowest level, Salience is tagging individual...



Share this page:
Follow us:
Task Runner