AkariAsai/unanswerable_qa
The official implementation for ACL 2021 "Challenges in Information Seeking QA: Unanswerable Questions and Paragraph Retrieval".
This project provides pre-annotated datasets and baseline models for understanding why some questions can't be answered by a given text. It takes a question and a body of text, then helps identify if the question is genuinely unanswerable from the text, or if the system just failed to find the answer. This is useful for researchers and developers working on improving search engines or question-answering systems.
No commits in the last 6 months.
Use this if you are a researcher or developer trying to build more robust information retrieval or question-answering systems that can intelligently handle unanswerable queries.
Not ideal if you are looking for an out-of-the-box question-answering system to deploy for end-users, as this focuses on research and analysis.
Stars
28
Forks
—
Language
Python
License
MIT
Category
Last pushed
Jun 19, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/AkariAsai/unanswerable_qa"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PaddlePaddle/RocketQA
🚀 RocketQA, dense retrieval for information retrieval and question answering, including both...
shuaihuaiyi/QA
使用深度å¦ä¹ 算法实现的ä¸æ–‡é—®ç”系统
allenai/deep_qa
A deep NLP library, based on Keras / tf, focused on question answering (but useful for other NLP too)
worldbank/iQual
iQual is a package that leverages natural language processing to scale up interpretative...
fhamborg/Giveme5W1H
Extraction of the journalistic five W and one H questions (5W1H) from news articles: who did...