SapienzaNLP/conception
Code and experiments for the COLING2020 paper "Conception: Multilingually-Enhanced, Human-Readable Concept Vector Representations".
This project helps natural language processing researchers create better representations of concepts across multiple languages. It takes text data in various languages and produces concept vectors that explicitly show relationships between ideas, even for languages with limited resources. Researchers working on multilingual NLP tasks, especially those dealing with semantic similarity or word sense disambiguation, would use this.
No commits in the last 6 months.
Use this if you need to build robust, language-independent concept representations for semantic analysis across many languages, including those with few available text resources.
Not ideal if you are only working with a single, high-resource language or if your primary goal is not concept-level semantic understanding.
Stars
11
Forks
1
Language
Java
License
—
Category
Last pushed
Dec 09, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/SapienzaNLP/conception"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
luheng/deep_srl
Code and pre-trained model for: Deep Semantic Role Labeling: What Works and What's Next
sileod/tasksource
Datasets collection and preprocessings framework for NLP extreme multitask learning
loomchild/maligna
Bilingual sengence aligner
CK-Explorer/DuoSubs
Semantic subtitle aligner and merger for bilingual subtitle syncing.
coastalcph/lex-glue
LexGLUE: A Benchmark Dataset for Legal Language Understanding in English