princeton-nlp/DensePhrases
[ACL 2021] Learning Dense Representations of Phrases at Scale; EMNLP'2021: Phrase Retrieval Learns Passage Retrieval, Too https://arxiv.org/abs/2012.12624
This tool helps you quickly find precise answers to your natural language questions within vast amounts of text, like all of Wikipedia. You provide a question or a statement, and it returns exact phrases, sentences, or even full documents as answers. It's designed for anyone needing fast, targeted information retrieval from large text corpora.
606 stars. No commits in the last 6 months.
Use this if you need to extract specific phrases or passages that directly answer questions or provide context from large document collections in real-time.
Not ideal if your primary goal is general document similarity search or if you are working with very small, niche text datasets.
Stars
606
Forks
75
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 15, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/princeton-nlp/DensePhrases"
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"
IndexFziQ/KMRC-Papers
A list of recent papers regarding knowledge-based machine reading comprehension.
danqi/rc-cnn-dailymail
CNN/Daily Mail Reading Comprehension Task
intfloat/SimKGC
ACL 2022, SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models