moreo
/
dante-verification
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge branch 'master' of https://github.com/AlexMoreo/dante-verification

This commit is contained in:
Alejandro Moreo Fernandez 2020-06-16 13:49:27 +02:00
parent 8d45db86b9 f0e596c1ac
commit b4209a15a0
1 changed files with 9 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
README.md
View File

@ -1,8 +1,6 @@
# Authorship Verification for Medieval Latin
Code to reproduce the experiments reported in the papers
["The Epistle to Cangrande Through the Lens of Computational Authorship Verification"](https://link.springer.com/chapter/10.1007/978-3-030-30754-7_15)
and
Code to reproduce the experiments reported in the paper
["L’Epistola a Cangrande al vaglio della Computational Authorship Verification: Risultati preliminari (con una postilla sulla cosiddetta XIV Epistola di Dante Alighieri)"](https://www.academia.edu/42297516/L_Epistola_a_Cangrande_al_vaglio_della_Computational_Authorship_Verification_risultati_preliminari_con_una_postilla_sulla_cosiddetta_XIV_Epistola_di_Dante_Alighieri_in_Nuove_inchieste_sull_Epistola_a_Cangrande_a_c._di_A._Casadei_Pisa_Pisa_University_Press_pp._153-192)
## Requirements:
@ -13,10 +11,8 @@ The experiments have been run using the following packages (older versions might
* scikit-learn==0.22.2.post1
* scipy==1.4.1
## Disclaimer:
The dataset is not distributed in this version. We have asked the Editors for permission to publish the corpus.
We are waiting for some of these responses to arrive.
## Dataset:
The dataset can be downloaded from [http://hlt.isti.cnr.it/medlatin/](http://hlt.isti.cnr.it/medlatin/).
## Running the Experiments
The script in __./src/author_identification.py__ executes the experiments. This is the script syntax (--help):
@ -44,7 +40,7 @@ optional arguments:
The following command line:
```
cd src
python author_identification.py ../Corpora/CorpusI Dante --unknown ../Epistle/EpistolaXIII_1.txt
python author_identification.py ../Corpora/MedLatin1 Dante --unknown ../Epistle/EpistolaXIII_1.txt
```
Will use all texts in ../Corpora/CorpusI as training documents to train a verificator for the
@ -56,18 +52,18 @@ to the positive class.
Similarly, the command line:
```
cd src
python author_identification.py ../Corpora/CorpusI ALL --loo
python author_identification.py ../Corpora/MedLatin1 ALL --loo
```
will perform a cross-validation of the binary classifier for all authors using all training documents in a leave-one-out (LOO) fashion.
The script will report the results both in the standard output (more elaborated) and in a log file. For example, the last command will produce a log file containing:
```
F1 for ClaraAssisiensis = 0.400
F1 for ClaraAssisiensis = 0.571
F1 for Dante = 0.957
F1 for GiovanniBoccaccio = 1.000
F1 for GuidoFaba = 0.974
F1 for GuidoFaba = 0.980
F1 for PierDellaVigna = 0.993
LOO Macro-F1 = 0.865
LOO Micro-F1 = 0.981
LOO Macro-F1 = 0.900
LOO Micro-F1 = 0.985
```
(Note that small numerical variations with respect to the original papers might occur due to different software versions and as a result from any stochastic underlying process. Those changes should anyway not alter the conclusions derived from the published results.)