IBM/transition-amr-parser
SoTA Abstract Meaning Representation (AMR) parsing with word-node alignments in Pytorch. Includes checkpoints and other tools such as statistical significance Smatch.
This tool helps natural language processing researchers and developers convert plain text into Abstract Meaning Representation (AMR) graphs. You input English or other supported language sentences or documents, and it outputs a graphical representation of their meaning in Penman notation. This is for users who need to analyze semantic structures in text for research or advanced language understanding tasks.
273 stars. No commits in the last 6 months.
Use this if you need to accurately convert raw text into a standardized semantic graph format (AMR) for deep linguistic analysis or advanced NLP applications.
Not ideal if you are looking for simple keyword extraction or sentiment analysis and don't require deep semantic parsing.
Stars
273
Forks
56
Language
Python
License
Apache-2.0
Category
Last pushed
Sep 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/IBM/transition-amr-parser"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
vunb/vntk
Vietnamese NLP Toolkit for Node
vncorenlp/VnCoreNLP
A Vietnamese natural language processing toolkit (NAACL 2018)
VinAIResearch/PhoNLP
PhoNLP: A BERT-based multi-task learning model for part-of-speech tagging, named entity...
nert-nlp/AMR-Bibliography
Organized inventory of research using the Abstract Meaning Representation
sheng-z/stog
AMR Parsing as Sequence-to-Graph Transduction