Skip to content

Commit

Permalink
Merge branch 'develop'
Browse files Browse the repository at this point in the history
  • Loading branch information
MichaelRoeder committed Oct 27, 2021
2 parents 9b3661e + 58a502f commit 1e1b109
Showing 1 changed file with 8 additions and 0 deletions.
8 changes: 8 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,14 @@ Please take a look at the the wikipage to read <a href="https://github.com/AKSW/

If you are using Palmetto for an experiment or something similar that leads to a publication, please cite the paper "Exploring the Space of Topic Coherence Measures" that you can find on the project website. A link to the project website is welcome as well :)

### Applicability

The coherence measures implemented with Palmetto mainly built on a reference index. This index is used to derive counts for the calculation of the coehrence values. These values can be used to measure the human interpretability of topics based on the topics' top words. It should be noted that the preprocessing of the index has an influence on the results.

_It is highly suggested to use an index that fits to the preprocessing that has been applied to the corpus on which the topics have been generated._

We use an English Wikipedia which has been preprocessed using a Lemmatizer. In practice, this means that word groups with non-lemmatized words may lead to unintuitive results simply because these word forms are underrepresented or even missing in our index (e.g., #57). In these cases, it is recommended to [generate an own index](https://github.com/dice-group/Palmetto/wiki/How-to-create-a-new-index).

### Directories

The `palmetto` directory contains the Palmetto library.
Expand Down

0 comments on commit 1e1b109

Please sign in to comment.