Commit Graph

54 Commits

Author SHA1 Message Date
andrea 66952820f9 running comparison with refactor branch 2021-01-29 12:30:31 +01:00
andrea 091101b39d running comparison with refactor branch 2021-01-29 11:37:42 +01:00
andrea 5906f85f33 branching to devel 2020-10-27 11:12:26 +01:00
andrea 526cf80b66 moved .sh files 2020-10-22 15:33:54 +02:00
andrea 90f24dab8e First commit 2020-10-22 15:11:49 +02:00
andrea 4a7a594a41 minor changes 2020-07-28 18:00:54 +02:00
andrea ba913f770a fixed train validation splitting 2020-07-27 17:15:06 +02:00
andrea c793bd30b5 gitignore 2020-07-27 12:20:59 +02:00
andrea f321e5ecde Updated .gitignore 2020-07-27 12:14:22 +02:00
andrea 92f16e60eb baseline multilingual Bert
removed some comments
2020-07-27 12:05:18 +02:00
andrea a594a84dab baseline multilingual Bert 2020-07-27 12:00:33 +02:00
andrea 9fd26e6ff7 Merge remote-tracking branch 'origin/master' 2020-07-27 12:00:14 +02:00
andrea d1fdad5f6e baseline multilingual Bert 2020-07-27 11:56:09 +02:00
andrea 2fc6373bff first commit 2020-04-06 12:12:47 +02:00
Alejandro Moreo Fernandez 22b7ea7e66 huge refactoring, deep learning, and other stuff 2020-01-30 17:08:52 +01:00
Alejandro Moreo Fernandez d249c4801f bugfix in muse extract method 2020-01-20 14:53:14 +01:00
Alejandro Moreo Fernandez 5bb5c913c0 assert added 2020-01-20 12:35:36 +01:00
Alejandro Moreo Fernandez c14e8226b1 refactor: added MUSE to learning/transformers.py 2020-01-20 12:32:47 +01:00
Alejandro Moreo Fernandez 9bf1986402 bugfix 2020-01-17 18:17:27 +01:00
Alejandro Moreo Fernandez 1ba5e60031 refactor 2020-01-17 18:16:29 +01:00
Alejandro Moreo Fernandez 73d1e70ae9 refactor 2020-01-16 17:28:54 +01:00
Alejandro Moreo Fernandez cfd3a609a2 merged? 2020-01-16 14:30:20 +01:00
Alejandro Moreo Fernandez e96968fc45 merging 2020-01-09 10:50:35 +01:00
andrea 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
andrea 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
andrea 56ee88220b typos 2019-12-17 10:42:29 +01:00
andrea a95511b4d9 sketched results reader - removed first tier learners optimization 2019-12-16 20:46:09 +01:00
andrea 174aa8ca05 Merge remote-tracking branch 'origin/master' 2019-12-12 14:34:54 +01:00
andrea 8940c99102 also saving n_components if auto optimizing it
removed some unnecessary columns from result csv
2019-12-12 14:33:41 +01:00
andrea dd34a96f87 also saving n_components if auto optimizing it
removed some unnecessary columns from result csv
2019-12-12 11:18:38 +01:00
Alejandro Moreo Fernandez a8d76b6f52 merged 2019-12-10 16:50:19 +01:00
Alejandro Moreo Fernandez 062f343664 divide by zero 2 2019-12-10 16:48:13 +01:00
Alejandro Moreo Fernandez 2bab6faf21 divide by zero 2019-12-10 16:47:30 +01:00
andrea 0c6056e7a1 refactored pca methods 2019-12-09 15:39:39 +01:00
andrea 9fa1899a7f refactored pca methods 2019-12-09 15:37:52 +01:00
andrea 509289b268 Plot variance explained by PCA for every language 2019-12-04 13:24:11 +01:00
andrea ba1a72ff94 Plot variance explained by PCA for every language 2019-12-04 10:16:17 +01:00
andrea f074fd97f9 get_optimal_supervised_components method - to be polished 2019-12-03 19:57:11 +01:00
andrea 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
andrea cf29826a32 Merge remote-tracking branch 'origin/master' 2019-12-02 12:41:22 +01:00
andrea e9404e2b8d mask_numbers method 2019-12-02 12:40:39 +01:00
Andrea Pedrotti 414e7f151e Delete results.csv 2019-11-30 19:23:39 +01:00
andrea fedc83f84e added col 'emebed_type' in csv results 2019-11-30 19:22:48 +01:00
andrea 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
andrea 601da33836 fixed embeddings remote import and dataset name in logfile 2019-11-28 23:10:14 +01:00
andrea df957e8448 typos 2019-11-28 19:33:04 +01:00
andrea b63159cd62 removed unnecessary dirs 2019-11-28 19:06:33 +01:00
andrea edf0d30b99 removed unnecessary dirs 2019-11-28 19:00:17 +01:00
andrea ab02566931 gitignore update 2019-11-28 18:56:06 +01:00