microsoft
/
nlp-recipes
зеркало из https://github.com/microsoft/nlp-recipes.git
1
0
Форкнуть 0
Код Задачи Пакеты Проекты Релизы Вики Активность
2 241 коммит 87 Ветки 7 Теги 49 MiB
Граф коммитов

2241 Коммитов

Автор SHA1 Сообщение Дата
Said Bleik 7db6d204e5
Merge pull request #612 from microsoft/staging 
Staging
 2021-01-06 16:17:23 -05:00
Said Bleik 54fc5d4cc0
Merge pull request #611 from microsoft/data-links-patch-1 
Update absa_azureml.ipynb
 2021-01-06 16:16:06 -05:00
Said Bleik 55d5020d6e
Update absa_azureml.ipynb 2021-01-06 16:14:30 -05:00
Said Bleik 52e751ac71
Merge pull request #605 from microsoft/emawa/feat/mnli-text-classification-mtdnn 
MTDNN Text classification notebook on MNLI dataset
 2020-06-29 01:03:47 -04:00
Emmanuel Awa cf062ee9f2 Remove genres reference 2020-06-29 04:55:31 +00:00
Emmanuel Awa c4b431820c Add text classification notebook with MTDNN on MNLI dataset 
- Computationally expensive as it runs on the entire MNLI train, test and dev datasets
 2020-06-28 23:38:31 +00:00
Said Bleik 5bd7127f54
Merge pull request #603 from microsoft/shchikke 
Changes NER notebook to use the dataset utilities
 2020-06-23 11:22:34 -04:00
Sharat Chikkerur 5c690efc9b reverted changes to dataset 2020-06-23 14:45:52 +00:00
Sharat Chikkerur d3e5350931 Merge branch 'staging' of github.com:microsoft/nlp-recipes into shchikke 2020-06-21 19:45:46 +00:00
Said Bleik 82ed6f58bb
Merge pull request #602 from microsoft/xnli-links-patch-1 
update xnli links
 2020-06-19 15:52:12 -04:00
Sharat Chikkerur 7fff3c7920 simplifying NER notebook by using dataset utilities 2020-06-19 18:29:19 +00:00
Sharat Chikkerur e46c8e846b simplifying NER notebook by using dataset utilities 2020-06-19 18:24:36 +00:00
Sharat Chikkerur b98e71ffc1 simplifying NER notebook by using dataset utilities 2020-06-19 18:23:46 +00:00
Said Bleik 6b099f4111
Merge pull request #585 from microsoft/update-package-patch-1 
Update absa.ipynb
 2020-06-19 10:06:36 -04:00
Said Bleik aff6c02b84
update xnli links 2020-06-18 13:53:51 -04:00
Said Bleik 3ea2ecdf1f
Merge pull request #595 from microsoft/sharatsc-patch-4 
Update link for MT-DNN
 2020-06-17 00:48:48 -04:00
Said Bleik 2c6baa59c4
Merge pull request #597 from microsoft/sharatsc-patch-6 
Adding additional models to text classification
 2020-06-17 00:48:09 -04:00
Said Bleik eedc2bc9fb
Merge pull request #598 from microsoft/sharatsc-patch-7 
Changing default model to distilbert
 2020-06-17 00:47:26 -04:00
Said Bleik 6a2274b52c
Merge pull request #600 from shanepeckham/patch-2 
Update NOTICE.txt
 2020-06-17 00:46:56 -04:00
Said Bleik aab6cf4af4
Merge pull request #599 from shanepeckham/patch-1 
Update remove_pixelserver.py
 2020-06-17 00:44:19 -04:00
Shane Peckham 6876e9f32a
Update NOTICE.txt 
Add spaCy license
 2020-06-16 19:14:46 +01:00
Shane Peckham 23cfc135c2
Update remove_pixelserver.py 2020-06-16 18:59:59 +01:00
Sharat Chikkerur 876d7cc1e1
Changing default model to distilbert 
Changing default model to distilbert to allow for faster experimentation times
 2020-06-15 22:18:18 -04:00
Sharat Chikkerur 34dd431bc3
Adding additional models to text classification 
Adding additional models for text classification. 
Also adding languages based on the list of currently supported models
['albert-base-v1',
 'albert-base-v2',
 'albert-large-v1',
 'albert-large-v2',
 'albert-xlarge-v1',
 'albert-xlarge-v2',
 'albert-xxlarge-v1',
 'albert-xxlarge-v2',
 'bart-large',
 'bart-large-cnn',
 'bart-large-mnli',
 'bart-large-xsum',
 'bert-base-cased',
 'bert-base-cased-finetuned-mrpc',
 'bert-base-chinese',
 'bert-base-dutch-cased',
 'bert-base-finnish-cased-v1',
 'bert-base-finnish-uncased-v1',
 'bert-base-german-cased',
 'bert-base-german-dbmdz-cased',
 'bert-base-german-dbmdz-uncased',
 'bert-base-japanese',
 'bert-base-japanese-char',
 'bert-base-japanese-char-whole-word-masking',
 'bert-base-japanese-whole-word-masking',
 'bert-base-multilingual-cased',
 'bert-base-multilingual-uncased',
 'bert-base-uncased',
 'bert-large-cased',
 'bert-large-cased-whole-word-masking',
 'bert-large-cased-whole-word-masking-finetuned-squad',
 'bert-large-uncased',
 'bert-large-uncased-whole-word-masking',
 'bert-large-uncased-whole-word-masking-finetuned-squad',
 'camembert-base',
 'distilbert-base-cased',
 'distilbert-base-cased-distilled-squad',
 'distilbert-base-german-cased',
 'distilbert-base-multilingual-cased',
 'distilbert-base-uncased',
 'distilbert-base-uncased-distilled-squad',
 'distilbert-base-uncased-finetuned-sst-2-english',
 'distilroberta-base',
 'flaubert-base-cased',
 'flaubert-base-uncased',
 'flaubert-large-cased',
 'flaubert-small-cased',
 'mbart-large-en-ro',
 'roberta-base',
 'roberta-base-openai-detector',
 'roberta-large',
 'roberta-large-mnli',
 'roberta-large-openai-detector',
 'umberto-commoncrawl-cased-v1',
 'umberto-wikipedia-uncased-v1',
 'xlm-clm-ende-1024',
 'xlm-clm-enfr-1024',
 'xlm-mlm-100-1280',
 'xlm-mlm-17-1280',
 'xlm-mlm-en-2048',
 'xlm-mlm-ende-1024',
 'xlm-mlm-enfr-1024',
 'xlm-mlm-enro-1024',
 'xlm-mlm-tlm-xnli15-1024',
 'xlm-mlm-xnli15-1024',
 'xlm-roberta-base',
 'xlm-roberta-large',
 'xlm-roberta-large-finetuned-conll02-dutch',
 'xlm-roberta-large-finetuned-conll02-spanish',
 'xlm-roberta-large-finetuned-conll03-english',
 'xlm-roberta-large-finetuned-conll03-german',
 'xlnet-base-cased',
 'xlnet-large-cased']
 2020-06-13 21:21:30 -04:00
Sharat Chikkerur 6131ad2509
Update link for MT-DNN 
Update link for MT-DNN
 2020-06-13 20:15:39 -04:00
Said Bleik a011680b0c
Merge pull request #593 from microsoft/emawa/mnli_download_preprocessed_tsv_data 
Feat: add functionality to download MNLI preprocessed tsv data.
 2020-06-11 09:49:17 -04:00
Said Bleik e1c476ff63
Merge pull request #594 from microsoft/update-notice-patch-1 
Update NOTICE.txt
 2020-06-11 09:49:02 -04:00
Said Bleik 96d1076405
Update NOTICE.txt 2020-06-10 23:10:04 -04:00
Emmanuel Awa 2091c3895e Feat: add functionality to download MNLI preprocessed tsv data. 
Leverage NYU Jiant Toolkit preprocessed tsv data source
 2020-06-08 17:38:50 +00:00
Said Bleik 0650ccf256
Merge pull request #592 from microsoft/add-xlm-cg-patch-1 
added xlm
 2020-06-01 13:26:15 -04:00
Said Bleik 6227ac0f84
added xlm 2020-06-01 12:56:00 -04:00
Said Bleik a5cd230318
Merge pull request #589 from microsoft/staging 
Staging to Master
 2020-05-20 10:29:21 -04:00
Said Bleik ab25969e51
Merge pull request #590 from microsoft/bleik/add-models 
Bleik/add models - minor edits
 2020-05-20 10:28:53 -04:00
saidbleik db9f076d68 minor edits 2020-05-20 14:26:05 +00:00
saidbleik af4df5c06f add load model fn 2020-05-20 14:23:25 +00:00
Said Bleik aa7340c34f
Merge pull request #588 from mikaelsouza/fixing-capitalization-and-table-headers 
Fixing capitalization and table headers
 2020-05-13 15:28:34 -04:00
Mikael Souza a363eca50d Added references table header 2020-05-13 12:01:16 -04:00
Mikael Souza 9d4743458e Fixed capitalization in README.md 2020-05-13 12:00:46 -04:00
Said Bleik e02e3b5525
Merge pull request #586 from microsoft/bleik/add-models 
update utils and examples
 2020-05-13 00:20:56 -04:00
Said Bleik 30afaa4619
Merge pull request #587 from microsoft/azure-pipelines 
Update gpu_unit_tests_linux.yml for Azure Pipelines
 2020-05-13 00:20:40 -04:00
Said Bleik b34a71566b
Merge branch 'staging' into azure-pipelines 2020-05-13 00:20:28 -04:00
Said Bleik cd50ef868d Update gpu_unit_tests_linux.yml for Azure Pipelines 2020-05-13 00:16:23 -04:00
saidbleik 2e92e319b3 Merge branch 'bleik/add-models' of https://github.com/microsoft/nlp-recipes into bleik/add-models 2020-05-12 22:06:45 +00:00
saidbleik ad323753e4 fix ner test 2020-05-12 22:06:10 +00:00
Said Bleik 477db37474
Merge branch 'staging' into bleik/add-models 2020-05-11 12:02:06 -04:00
saidbleik 9d9ef2001b resolve conflicts 2020-05-11 14:56:11 +00:00
saidbleik 78726ff471 update summarization models 2020-05-08 22:38:54 +00:00
saidbleik 8f965d44e5 qa updates 2020-05-08 20:12:04 +00:00
saidbleik c1aaf2592e common updates 2020-05-08 20:11:34 +00:00
saidbleik e418fc9b75 update seq classification utils 2020-05-08 17:33:28 +00:00