julien-c HF staff commited on
Commit
2ec9b33
1 Parent(s): 3f1ec3d

Migrate model card from transformers-repo

Browse files

Read announcement at https://discuss.huggingface.co/t/announcement-all-model-cards-will-be-migrated-to-hf-co-model-repos/2755
Original file history: https://github.com/huggingface/transformers/commits/master/model_cards/jcblaise/bert-tagalog-base-cased-WWM/README.md

Files changed (1) hide show
  1. README.md +62 -0
README.md ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: tl
3
+ tags:
4
+ - bert
5
+ - tagalog
6
+ - filipino
7
+ license: gpl-3.0
8
+ inference: false
9
+ ---
10
+
11
+ # BERT Tagalog Base Cased (Whole Word Masking)
12
+ Tagalog version of BERT trained on a large preprocessed text corpus scraped and sourced from the internet. This model is part of a larger research project. We open-source the model to allow greater usage within the Filipino NLP community. This particular version uses whole word masking.
13
+
14
+ ## Usage
15
+ The model can be loaded and used in both PyTorch and TensorFlow through the HuggingFace Transformers package.
16
+
17
+ ```python
18
+ from transformers import TFAutoModel, AutoModel, AutoTokenizer
19
+
20
+ # TensorFlow
21
+ model = TFAutoModel.from_pretrained('jcblaise/bert-tagalog-base-cased-WWM', from_pt=True)
22
+ tokenizer = AutoTokenizer.from_pretrained('jcblaise/bert-tagalog-base-cased-WWM', do_lower_case=False)
23
+
24
+ # PyTorch
25
+ model = AutoModel.from_pretrained('jcblaise/bert-tagalog-base-cased-WWM')
26
+ tokenizer = AutoTokenizer.from_pretrained('jcblaise/bert-tagalog-base-cased-WWM', do_lower_case=False)
27
+ ```
28
+ Finetuning scripts and other utilities we use for our projects can be found in our centralized repository at https://github.com/jcblaisecruz02/Filipino-Text-Benchmarks
29
+
30
+ ## Citations
31
+ All model details and training setups can be found in our papers. If you use our model or find it useful in your projects, please cite our work:
32
+
33
+ ```
34
+ @inproceedings{localization2020cruz,
35
+ title={{Localization of Fake News Detection via Multitask Transfer Learning}},
36
+ author={Cruz, Jan Christian Blaise and Tan, Julianne Agatha and Cheng, Charibeth},
37
+ booktitle={Proceedings of The 12th Language Resources and Evaluation Conference},
38
+ pages={2589--2597},
39
+ year={2020},
40
+ url={https://www.aclweb.org/anthology/2020.lrec-1.315}
41
+ }
42
+
43
+ @article{cruz2020establishing,
44
+ title={Establishing Baselines for Text Classification in Low-Resource Languages},
45
+ author={Cruz, Jan Christian Blaise and Cheng, Charibeth},
46
+ journal={arXiv preprint arXiv:2005.02068},
47
+ year={2020}
48
+ }
49
+
50
+ @article{cruz2019evaluating,
51
+ title={Evaluating Language Model Finetuning Techniques for Low-resource Languages},
52
+ author={Cruz, Jan Christian Blaise and Cheng, Charibeth},
53
+ journal={arXiv preprint arXiv:1907.00409},
54
+ year={2019}
55
+ }
56
+ ```
57
+
58
+ ## Data and Other Resources
59
+ Data used to train this model as well as other benchmark datasets in Filipino can be found in my website at https://blaisecruz.com
60
+
61
+ ## Contact
62
+ If you have questions, concerns, or if you just want to chat about NLP and low-resource languages in general, you may reach me through my work email at jan_christian_cruz@dlsu.edu.ph