53198a7e2c
implemented method to compute WCE only for well represented classes;
...
refactored MLE class in order to support WCE, standard embeddings and combinations;
sketched out NN implementation for WE compositionality;
still TODO SIF embeddings;
2020-01-07 17:05:41 +01:00
0e66fbf197
implemented method to compute WCE only for well represented classes -
...
refactored MLE class in order to support WCE, standard embeddings and combinations
2019-12-29 11:54:05 +01:00
a95511b4d9
sketched results reader - removed first tier learners optimization
2019-12-16 20:46:09 +01:00
8940c99102
also saving n_components if auto optimizing it
...
removed some unnecessary columns from result csv
2019-12-12 14:33:41 +01:00
dd34a96f87
also saving n_components if auto optimizing it
...
removed some unnecessary columns from result csv
2019-12-12 11:18:38 +01:00
9fa1899a7f
refactored pca methods
2019-12-09 15:37:52 +01:00
509289b268
Plot variance explained by PCA for every language
2019-12-04 13:24:11 +01:00
f074fd97f9
get_optimal_supervised_components method - to be polished
2019-12-03 19:57:11 +01:00
4de6b3e250
refactoring emebed method into Class StorageEmbeddings. refactoring class EmbeddingsAligned.
...
tSVD and T-SNE for supervised embeddings
2019-12-03 15:34:12 +01:00
fedc83f84e
added col 'emebed_type' in csv results
2019-11-30 19:22:48 +01:00
f2083bf22a
reworked unsupervised (aligned) embeddings loader method and class (fastText and MUSE).
...
new op.arg -t ['MUSE', 'FastText']
uploaded /results/results.csv (on rcv1 ... run0.pickle) obtained on all available setup.
TODO: refactor it also as a standalone class with its own load/weighted sum/extract/reduce methods.
2019-11-30 19:14:51 +01:00
Alejandro Moreo Fernandez
499c6018c0
standardization
2019-11-29 18:14:14 +01:00
601da33836
fixed embeddings remote import and dataset name in logfile
2019-11-28 23:10:14 +01:00
df957e8448
typos
2019-11-28 19:33:04 +01:00
2a5d0243db
first commit
2019-11-28 18:39:19 +01:00
andrea
Alejandro Moreo Fernandez