timpal0l/xlm-roberta-base-faq-extractor

Frequently Asked Questions classifier

This model is trained to determine whether a question/statement is a FAQ, in the domain of products, businesses, website faqs, etc. For e.g "What is the warranty of your product?" In contrast, daily questions such as "how are you?", "what is your name?", or simple statements such as "this is a tree".

Usage

from transformers import pipeline

classifier = pipeline("text-classification", "timpal0l/xlm-roberta-base-faq-extractor")
label_map = {"LABEL_0" : False, "LABEL_1" : True}

documents = ["What is the warranty for iPhone15?", 
             "How old are you?", 
             "Nice to meet you", 
             "What is your opening hours?", 
             "What is your name?", 
             "The weather is nice"]

predictions = classifier(documents)

for p, d in zip(predictions, documents):
    print(d, "--->", label_map[p["label"]])

What is the warranty for iPhone15? ---> True
How old are you? ---> False
Nice to meet you ---> False
What is your opening hours? ---> True
What is your name? ---> False
The weather is nice ---> False