Spanish punctuation and capitalisation restoration model
Details of the model
This is a reduced version of the Spanish capitalisation and punctuation restoration model developed by VÓCALI as part of the SANIVERT project.
You can try the model in the following SPACE
Details of the dataset
This is a dccuchile/bert-base-spanish-wwm-uncased model fine-tuned for punctuation restoration using the following data distribution.
| Language | Number of text samples | Number of tokens |
|---|---|---|
| Spanish | 2,153,296 | 51,049,602 |
Evaluation Metrics
The metrics used to the evaluation of the model are the Macro and the Weighted F1 scores.
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
from transformers import pipeline, AutoModelForTokenClassification, AutoTokenizer
import torch
def get_result_text_es_pt (list_entity, text, lang):
result_words = []
tmp_word = ""
if lang == "es":
punc_tags = ['¿', '?', '¡', '!', ',', '.', ':']
else:
punc_tags = ['?', '!', ',', '.', ':']
for idx, entity in enumerate(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 tmp_word == "":
p_s = list_entity[idx-1]["start"]
p_e = list_entity[idx-1]["end"]
tmp_word = text[p_s:p_e] + text[start:end]
else:
tmp_word = tmp_word + text[start:end]
word = tmp_word
else:
tmp_word = ""
word = 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 = "es"
model_path = "VOCALINLP/spanish_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 = "el paciente presenta los siguientes síntomas náuseas vértigo disnea fiebre y dolor abdominal"
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.