utahnlp/knowledge_infotabs
Repository containing code for the NAACL 2021 paper (Incorporating External Knowledge to Enhance Tabular Reasoning)
This project helps data analysts and researchers automatically interpret and reason with information presented in tables. It takes raw tabular data and associated text descriptions, processes them to identify key relationships and facts, and then generates structured outputs that explain the connections. This is especially useful for anyone who needs to quickly understand complex datasets and draw conclusions without extensive manual review.
No commits in the last 6 months.
Use this if you need to extract logical conclusions and insights from semi-structured tables by incorporating external knowledge for better reasoning.
Not ideal if your data is unstructured free-form text or if you only need basic data extraction without complex inferential reasoning.
Stars
17
Forks
5
Language
Python
License
MIT
Category
Last pushed
Jun 20, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/utahnlp/knowledge_infotabs"
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)
princeton-nlp/DensePhrases
[ACL 2021] Learning Dense Representations of Phrases at Scale; EMNLP'2021: Phrase Retrieval...
thunlp/MultiRD
Code and data of the AAAI-20 paper "Multi-channel Reverse Dictionary Model"
IndexFziQ/KMRC-Papers
A list of recent papers regarding knowledge-based machine reading comprehension.
danqi/rc-cnn-dailymail
CNN/Daily Mail Reading Comprehension Task