seominjoon/denspi
Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index (DenSPI)
This project helps anyone who needs to quickly find specific answers to natural language questions within a vast collection of documents like Wikipedia. You input a question, and it provides a precise phrase from the source document that directly answers it, much faster than traditional search and read methods. It's designed for information specialists, researchers, or anyone needing instant factual lookup from extensive textual data.
200 stars. No commits in the last 6 months.
Use this if you need real-time, precise answers to open-ended questions from a very large text corpus, where speed and accuracy of direct phrase retrieval are critical.
Not ideal if your goal is to summarize information, engage in conversational AI, or if you don't have the significant hardware resources (1.5TB storage, 30GB RAM) required to host the index.
Stars
200
Forks
24
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 06, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/seominjoon/denspi"
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...