A french sentiment analysis model, based on
CamemBERT
, and finetuned on a large-scale dataset scraped from
Allociné.fr
user reviews.
Results
Validation Accuracy
Validation F1-Score
Test Accuracy
Test F1-Score
97.39
97.36
97.44
97.34
The dataset and the evaluation code are available on
this repo
.
Usage
from transformers import AutoTokenizer, TFAutoModelForSequenceClassification
from transformers import pipeline
tokenizer = AutoTokenizer.from_pretrained("tblard/tf-allocine")
model = TFAutoModelForSequenceClassification.from_pretrained("tblard/tf-allocine")
nlp = pipeline('sentiment-analysis', model=model, tokenizer=tokenizer)
print(nlp("Alad'2 est clairement le meilleur film de l'année 2018.")) # POSITIVEprint(nlp("Juste whoaaahouuu !")) # POSITIVEprint(nlp("NUL...A...CHIER ! FIN DE TRANSMISSION.")) # NEGATIVEprint(nlp("Je m'attendais à mieux de la part de Franck Dubosc !")) # NEGATIVE
More Information About tf-allocine huggingface.co Model
tf-allocine huggingface.co
tf-allocine huggingface.co is an AI model on huggingface.co that provides tf-allocine's model effect (), which can be used instantly with this tblard tf-allocine model. huggingface.co supports a free trial of the tf-allocine model, and also provides paid use of the tf-allocine. Support call tf-allocine model through api, including Node.js, Python, http.
tf-allocine huggingface.co is an online trial and call api platform, which integrates tf-allocine's modeling effects, including api services, and provides a free online trial of tf-allocine, you can try tf-allocine online for free by clicking the link below.
tblard tf-allocine online free url in huggingface.co:
tf-allocine is an open source model from GitHub that offers a free installation service, and any user can find tf-allocine on GitHub to install. At the same time, huggingface.co provides the effect of tf-allocine install, users can directly use tf-allocine installed effect in huggingface.co for debugging and trial. It also supports api for free installation.