bernhard2202/rankqa

This is the PyTorch implementation of the ACL 2019 paper RankQA: Neural Question Answering with Answer Re-Ranking.

34
/ 100
Emerging

This project helps researchers and developers working with question answering systems to improve the accuracy of their results. It takes existing question-text pairs and their initial predicted answers, then applies an additional re-ranking step using a combination of features. The output is a refined list of answers, ordered by their likelihood. This is primarily for natural language processing (NLP) researchers and engineers building or evaluating advanced QA systems.

No commits in the last 6 months.

Use this if you are building a neural question-answering system and want to boost the accuracy of the extracted answers beyond what traditional two-stage retrieval and comprehension models offer.

Not ideal if you are looking for an out-of-the-box, end-user question-answering tool without needing to integrate it into an existing NLP pipeline.

natural-language-processing information-retrieval machine-comprehension answer-ranking text-analytics
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

83

Forks

15

Language

Python

License

Last pushed

Dec 13, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/bernhard2202/rankqa"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.