thunlp/CokeBERT
CokeBERT: Contextual Knowledge Selection and Embedding towards Enhanced Pre-Trained Language Models
This project helps improve the understanding of text by incorporating factual knowledge from external sources. It takes your raw text data and a knowledge graph (like a database of facts and their relationships) to produce an enriched language model. This model is more accurate in tasks like named entity recognition or relation extraction, making it valuable for data scientists and NLP engineers building advanced language understanding systems.
No commits in the last 6 months.
Use this if you need to build highly accurate natural language understanding models where integrating external factual knowledge can significantly improve performance on specific tasks.
Not ideal if your primary goal is general text generation or if you don't have access to a relevant knowledge graph for your domain.
Stars
31
Forks
9
Language
Python
License
—
Category
Last pushed
Jul 02, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/thunlp/CokeBERT"
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