Update README.md
Browse files
README.md
CHANGED
@@ -28,8 +28,8 @@ from transformers import RobertaTokenizerFast, RobertaForTokenClassification
|
|
28 |
from attacut import tokenize
|
29 |
import torch
|
30 |
|
31 |
-
tokenizer = RobertaTokenizerFast.from_pretrained("
|
32 |
-
model = RobertaForTokenClassification.from_pretrained("
|
33 |
```
|
34 |
|
35 |
To do Sentence Boundary Classification, use the following commands
|
@@ -73,11 +73,11 @@ print(nlp(inputList))
|
|
73 |
|
74 |
# Huggingface Models
|
75 |
1. `HoogBERTaEncoder`
|
76 |
-
- [HoogBERTa](https://huggingface.co/
|
77 |
2. `HoogBERTaMuliTaskTagger`:
|
78 |
-
- [HoogBERTa-NER-lst20](https://huggingface.co/
|
79 |
-
- [HoogBERTa-POS-lst20](https://huggingface.co/
|
80 |
-
- [HoogBERTa-SENTENCE-lst20](https://huggingface.co/
|
81 |
|
82 |
|
83 |
# Citation
|
|
|
28 |
from attacut import tokenize
|
29 |
import torch
|
30 |
|
31 |
+
tokenizer = RobertaTokenizerFast.from_pretrained("lst-nectec/HoogBERTa-SENTENCE-lst20")
|
32 |
+
model = RobertaForTokenClassification.from_pretrained("lst-nectec/HoogBERTa-SENTENCE-lst20")
|
33 |
```
|
34 |
|
35 |
To do Sentence Boundary Classification, use the following commands
|
|
|
73 |
|
74 |
# Huggingface Models
|
75 |
1. `HoogBERTaEncoder`
|
76 |
+
- [HoogBERTa](https://huggingface.co/lst-nectec/HoogBERTa): `Feature Extraction` and `Mask Language Modeling`
|
77 |
2. `HoogBERTaMuliTaskTagger`:
|
78 |
+
- [HoogBERTa-NER-lst20](https://huggingface.co/lst-nectec/HoogBERTa-NER-lst20): `Named-entity recognition (NER)` based on LST20
|
79 |
+
- [HoogBERTa-POS-lst20](https://huggingface.co/lst-nectec/HoogBERTa-POS-lst20): `Part-of-speech tagging (POS)` based on LST20
|
80 |
+
- [HoogBERTa-SENTENCE-lst20](https://huggingface.co/lst-nectec/HoogBERTa-SENTENCE-lst20): `Clause Boundary Classification` based on LST20
|
81 |
|
82 |
|
83 |
# Citation
|