Commit 76b81edc authored by Victor Zimmermann's avatar Victor Zimmermann
Browse files

Update README.md

parent 8a2664e6
Loading
Loading
Loading
Loading
+33 −5
Original line number Diff line number Diff line
@@ -28,7 +28,8 @@ Change to source directory.
$ cd absinth/src
```

Run setup.sh.
Run setup.sh. This installs mandatory modules and creates folders for
temporary output.

```
$ bash setup.sh
@@ -52,20 +53,47 @@ $ python3 absinth.py
$ python3 absinth.py -t
```

Absinth may utilise multiprocessing for parallel topic processing. Simply put
'-p' followed by the number of processes after the program name.

```
$ python3 absinth.py -p 4
```

Absinth produces individual clustering files for every target. To merge the 
output files, simple call merge.py
output files, simple call merge.py. The resulting output for the WSI-evaluator
is placed in the 'absinth/src/final' directory.

```
$ python3 merge.py
```

Absinth does not overwrite already processed topics. Please delete files you
wish to replace manually.

## Baseline

Our baseline 'abstinent.py' works in much the same way as absinth.py. Not all
variables in config.py are supported in our baseline though.

```
$ python3 abstinent.py -t -p 3
```

To merge the abstinent.py output, simply put the '-bl' mofifier after merge.py:

```
$ python3 merge.py -bl
```

View the documentation for more information.

## Built With

* [NetworkX](https://networkx.github.io/) - Graph implementation
* [NLTK](http://www.nltk.org/) - Stopwords
* [Spacy](https://spacy.io/) - Tokenisation and syntactic parsing
* [NumPy](http://www.numpy.org/) - Maths
* [MatPlotLib](https://matplotlib.org/) - Visualisation
* [SciPy](https://www.scipy.org/) - More maths

## References

@@ -84,7 +112,7 @@ Véronis, Jean. (2004). HyperLex: Lexical cartography for information retrieval.

## License

This project is licensed under the MIT License - see the [LICENSE.md](LICENSE.md) file for details
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details

## Acknowledgments