Piotr Czapla
a948d7df91
Merge branch 'master' of https://github.com/n-waves/ulmfit-multilingual
2019-03-26 21:29:33 +01:00
Piotr Czapla
66ec30a122
Add more results
2019-03-26 21:27:18 +01:00
NAUSICAA\Julian
43588b43e1
Move logs
2019-03-07 13:19:40 -03:00
NAUSICAA\Julian
227f3b5dff
Merge branch 'master' of https://github.com/n-waves/ulmfit-multilingual into text_cols
2019-03-07 13:18:52 -03:00
Julian Eisenschlos
e793425ef7
Merge pull request #37 from n-waves/qrnn_perf
...
QRNN Time Performance Benchark
2019-03-01 18:06:13 -03:00
Piotr Czapla
7b2ac9e94b
Add ability to use random-init=True
2019-03-01 17:41:07 +01:00
Piotr Czapla
11b2b14523
Fix -m ulmfit tar method
2019-03-01 17:39:58 +01:00
NAUSICAA\Julian
02522fcd44
Rename file
2019-02-28 08:17:41 -03:00
NAUSICAA\Julian
71e7637dd0
CLS Results
2019-02-27 23:44:28 -03:00
Piotr Czapla
4742a68d28
Some logs from previous experiments
2019-02-27 20:31:38 +01:00
Piotr Czapla
260faa703c
Correct the label smoothing implementation
2019-02-22 16:55:35 +01:00
Piotr Czapla
c69d31c420
New results lstm 30k 1cyc
2019-02-22 12:01:25 +01:00
NAUSICAA\Julian
61ae344fda
Remove fastai warning
2019-02-20 17:02:56 -03:00
NAUSICAA\Julian
c698c97772
Adding logs
2019-02-20 17:02:02 -03:00
NAUSICAA\Julian
b39fb5390b
Adding QRNN benchmark
2019-02-20 15:21:58 -03:00
Piotr Czapla
c29180a08f
Add some results
2019-02-20 10:22:44 +01:00
Piotr Czapla
0dda4b4c2c
Zeroshot MLDoc results for ulmfit trained on 10k examples
2019-02-17 19:03:02 +01:00
Julian Eisenschlos
b7e3a5e7a4
Update BERT Zero-shot results
2019-02-16 14:42:40 -03:00
Julian Eisenschlos
be0511e42b
Adding Bert results
2019-02-15 15:51:35 -03:00
Piotr Czapla
0f084168c1
Merge branch 'master' of https://github.com/n-waves/ulmfit-multilingual
2019-02-14 22:35:29 +01:00
Piotr Czapla
cd47b3b5dc
Fix use_moses=True for mldoc so that it is identical to wiki with uses_moses=False
...
The issue was that Moses was executed after pre_rules when use_moses = True, But when data set was pre tokenized with Moses (use_moses=False) the pre_rules were executed after.
So our wikipedia had the following processing:
- raw text
- Moses
- pre_rules
- split(' ') # fastai BaseTokenizer
- post_rules
- sentence piece
While mldoc had the following tokenziation
- raw text
- pre_rules
- Moses
- post_rules
- sentence piece
After fix I've retrained the classfiers (without finetuning) and I haven't notice huge changes in the performance. 4 languages received slight improvment 4 got a slight decrease in performance.
2019-02-14 22:35:20 +01:00
Marcin
72e86cefc9
Add QRNN LM results for Italian
2019-02-14 12:48:04 +01:00
Marcin
0535ef169a
QRNN mldoc results for de, en and es
2019-02-14 11:05:02 +01:00
Marcin
9d893e393b
Add QRNN results
2019-02-14 00:00:43 +01:00
Piotr Czapla
b14a393671
Add more results including full zeroshot results
2019-02-13 15:29:16 +01:00
Piotr Czapla
4e1b76feee
Add MLDoc summary & zeroshot logs
2019-02-12 15:01:42 +01:00
Piotr Czapla
e72cdfb6db
Add result logs (it)
2019-02-12 15:01:22 +01:00
Piotr Czapla
a1e7a79b57
Add result logs
2019-02-12 15:00:29 +01:00
Piotr Czapla
22e40d81f3
Additional DE results and first results on FR and JA
2019-02-11 10:51:42 +01:00
Piotr Czapla
e7ec9f0233
fix markdown formatting
2019-02-10 10:52:03 +01:00
Piotr Czapla
07ab9ccaf8
Add first MLDoc results
2019-02-10 09:53:42 +01:00
Piotr Czapla
672ef2d59f
Remove old result logs
2019-02-10 09:53:26 +01:00
Piotr Czapla
83427aadc6
Add moses with fastai preprocessing
2018-12-02 21:43:57 +01:00
Piotr Czapla
2bde30a402
Add experiment with biclassifier (concat)
2018-11-19 15:31:10 +01:00
Piotr Czapla
9f526a9849
Add experiment where wd_true is set to True.
2018-11-19 15:30:28 +01:00
Piotr Czapla
c821d2e783
first version of bi classifier
2018-11-19 09:59:08 +01:00
Piotr Czapla