krystalan/Multi-hopRC
:notebook_with_decorative_cover: notes for Multi-hop Reading Comprehension and open-domain question answering
This project compiles resources and research papers on multi-hop reading comprehension, a technique where an AI system answers questions by piecing together information from multiple sources, similar to how a human synthesizes information. It takes various forms of text (like articles, dialogue, or even tables) and a question, then provides an answer that requires connecting several pieces of information. This is valuable for researchers and practitioners working on advanced AI for information retrieval and complex question answering.
No commits in the last 6 months.
Use this if you are a researcher or AI practitioner looking to understand and implement advanced multi-hop question answering systems that require synthesizing information across multiple documents.
Not ideal if you are looking for an out-of-the-box software tool to directly apply for simple, single-document question answering tasks.
Stars
90
Forks
8
Language
—
License
—
Category
Last pushed
Apr 21, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/krystalan/Multi-hopRC"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ymcui/cmrc2018
A Span-Extraction Dataset for Chinese Machine Reading Comprehension (CMRC 2018)
thunlp/MultiRD
Code and data of the AAAI-20 paper "Multi-channel Reverse Dictionary Model"
princeton-nlp/DensePhrases
[ACL 2021] Learning Dense Representations of Phrases at Scale; EMNLP'2021: Phrase Retrieval...
IndexFziQ/KMRC-Papers
A list of recent papers regarding knowledge-based machine reading comprehension.
danqi/rc-cnn-dailymail
CNN/Daily Mail Reading Comprehension Task