File size: 3,085 Bytes
8ced499 211be49 8ced499 2be935d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 |
---
widget:
- text: teve alguma doença na última semana
example_title: Example 1
- text: sofre da doença de parkinson
example_title: Example 2
- text: é preciso fazer análises ao sangue à urina e aos ouvidos
example_title: Example 3
language:
- pt
---
# Portuguese punctuation and capitalisation restoration model
## Details of the model
This is a reduced version of the Portuguese capitalisation and punctuation restoration model developed by [VÓCALI](https://www.vocali.net) as part of the SANIVERT project.
You can try the model in the following [SPACE](https://huggingface.co/spaces/VOCALINLP/punctuation_and_capitalization_restoration_sanivert)
## Details of the dataset
## Evaluation Metrics
## Funding
This work was funded by the Spanish Government, the Spanish Ministry of Economy and Digital Transformation through the Digital Transformation through the "Recovery, Transformation and Resilience Plan" and also funded by the European Union NextGenerationEU/PRTR through the research project 2021/C005/0015007
## How to use the model
```py
from transformers import pipeline, AutoModelForTokenClassification, AutoTokenizer
import torch
def get_result_text_es_pt (list_entity, text, lang):
result_words = []
if lang == "es":
punc_tags = ['¿', '?', '¡', '!', ',', '.', ':']
else:
punc_tags = ['?', '!', ',', '.', ':']
for entity in list_entity:
tag = entity["entity"]
word = entity["word"]
start = entity["start"]
end = entity["end"]
# check punctuation
punc_in = next((p for p in punc_tags if p in tag), "")
subword = False
# check subwords
if word[0] == "#":
subword = True
if punc_in != "":
word = result_words[-1].replace(punc_in, "") + text[start:end]
else:
word = result_words[-1] + text[start:end]
if tag == "l":
word = word
elif tag == "u":
word = word.capitalize()
# case with punctuation
else:
if tag[-1] == "l":
word = (punc_in + word) if punc_in in ["¿", "¡"] else (word + punc_in)
elif tag[-1] == "u":
word = (punc_in + word.capitalize()) if punc_in in ["¿", "¡"] else (word.capitalize() + punc_in)
if subword == True:
result_words[-1] = word
else:
result_words.append(word)
return " ".join(result_words)
lang = "pt"
model_path = "VOCALINLP/portuguese_capitalization_punctuation_restoration_sanivert"
model = AutoModelForTokenClassification.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path)
pipe = pipeline("token-classification", model=model, tokenizer=tokenizer)
text = "é preciso fazer análises ao sangue à urina e aos ouvidos"
result = pipe(text)
print("Source text: "+ text)
result_text = get_result_text_es_pt(result, text, lang)
print("Restored text: " +result_text)
```
> Created by [VOCALI SISSTEMAS INTELIGENTES S.L.](https://www.vocali.net) |