Boolean Question

Get accurate answer prediction for True / False question using this python pytorch model. The model takes a passage and question as input and returns either "True" or "False" as predicted answer. Model used is RoBERTa that is further trained on BoolQ dataset.

Installation

Install it with python package installer pip

pip install boolean_question

or install the latest master branch

pip install git+https://github.com/Saadmairaj/boolean-question

Usage

The usage is simple and straight forward, import BoolQ class model and pass arguments to the BoolQ.predict(passage: str, question: str) method to predict the boolean answer "True" or "False"

import pprint
from boolean_question import BoolQ

bq = BoolQ()

passage = """
A red dwarf is the smallest and coolest kind of star on the main sequence.
Red dwarfs are by far the most common type of star in the Milky Way, at
least in the neighborhood of the Sun, but because of their low luminosity,
individual red dwarfs cannot be easily observed."""

question = "Coolest star in the Milky way is a Red dwarf"

# Predict the answer from the passage and the question
ans = bq.predict(passage, question)
print(ans)

# After prediction extra details of the prediction can be seen with the below command
pprint.pprint(bq.prediction_details())

View output

True
{'answer': True,
'confidence': None,
'false confidence': 0.01,
'passage': '\n'
            'A red dwarf is the smallest and coolest kind of star on the main '
            'sequence. Red dwarfs are by far the most common type of star in \n'
            'the Milky Way, at least in the neighborhood of the Sun, but '
            'because of their low luminosity, individual red dwarfs cannot '
            'be \n'
            'easily observed.',
'question': 'Coolest star in the Milky way is a Red dwarf',
'true confidence': 0.99}

Metadata

Release files for boolean-question 0.0.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for boolean-question 0.0.3
File	Size	Uploaded
boolean_question-0.0.3.tar.gz	9.3 kB	Aug 15, 2022	Details

Built distribution (wheel)

Table of built distributions (wheels) for boolean-question 0.0.3
File	Interpreter	ABI	Platform	Reset
boolean_question-0.0.3-py3-none-any.whl 11.3 kB Aug 15, 2022	Python 3	none	any	Details

Total release size: 20.6 kB

Release files / boolean_question-0.0.3.tar.gz

Download URL	boolean_question-0.0.3.tar.gz
Size	9.3 kB
Tags	Source
SHA-256 checksum How to use checksums	`667b2d289c7bb4726a5040f6d12305b18b36e0c05d7b462edf94ce6f63a89c5c`
BLAKE2b-256 checksum How to use checksums	`dfc68bb430b9cffb29743e1a1a735af8b9636a3e5549b65dec8ec593886938c5`
Upload date	Aug 15, 2022
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/4.0.1 CPython/3.8.13`

Release files / boolean_question-0.0.3-py3-none-any.whl

Download URL	boolean_question-0.0.3-py3-none-any.whl
Size	11.3 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`d9a561ce891fe054167b0442c389b49e99578d64e60655673f38030adf37cfa9`
BLAKE2b-256 checksum How to use checksums	`10ece488a47d6b7597087e36277945912f250727036a9cc0a8a63d9dbb85324b`
Upload date	Aug 15, 2022
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/4.0.1 CPython/3.8.13`