lesterpjy/numeric-t5
Training T5 to perform numerical reasoning.
This project offers a specialized natural language processing model that can answer questions requiring numerical reasoning directly from text. You input a document and a question, and it provides a precise numerical answer, even if it needs to perform calculations not explicitly stated in the text. This is designed for researchers or practitioners working with text-based data where extracting and calculating specific numbers is crucial.
No commits in the last 6 months.
Use this if you need to automatically extract and calculate numerical answers from text passages, rather than just locating text spans or generating mathematical equations.
Not ideal if your questions are purely about general reading comprehension without any numerical computation involved.
Stars
23
Forks
1
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jun 04, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/lesterpjy/numeric-t5"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
asahi417/lm-question-generation
Multilingual/multidomain question generation datasets, models, and python library for question...
SparkJiao/SLQA
An Unofficial Pytorch Implementation of Multi-Granularity Hierarchical Attention Fusion Networks...
MurtyShikhar/Question-Answering
TensorFlow implementation of Match-LSTM and Answer pointer for the popular SQuAD dataset.
hsinyuan-huang/FlowQA
Implementation of conversational QA model: FlowQA (with slight improvement)
allenai/aokvqa
Official repository for the A-OKVQA dataset