ringgaard/sling
SLING - A natural language frame semantics parser
This project helps knowledge base engineers automatically extract structured facts from large text corpuses like Wikipedia. It takes raw text dumps and converts them into structured annotations and frame semantic graphs, which can then be used to populate or complete knowledge bases like Wikidata. The primary user would be a knowledge engineer or data scientist focused on large-scale information extraction and knowledge graph construction.
174 stars.
Use this if you need to process vast amounts of text, such as encyclopedic articles, to automatically identify and extract facts for populating a knowledge base.
Not ideal if you're looking for a simple, off-the-shelf system to extract facts from arbitrary, unstructured text without significant development work.
Stars
174
Forks
11
Language
C++
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/ringgaard/sling"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
facebookresearch/stopes
A library for preparing data for machine translation research (monolingual preprocessing,...
Droidtown/ArticutAPI
API of Articut 中文斷詞 (兼具語意詞性標記)：「斷詞」又稱「分詞」，是中文資訊處理的基礎。Articut 不用機器學習，不需資料模型，只用現代白話中文語法規則，即能達到...
rkcosmos/deepcut
A Thai word tokenization library using Deep Neural Network
fukuball/jieba-php
"結巴"中文分詞：做最好的 PHP 中文分詞、中文斷詞組件。 / "Jieba" (Chinese for "to stutter") Chinese text segmentation:...
pytorch/text
Models, data loaders and abstractions for language processing, powered by PyTorch