luheng/deep_srl
Code and pre-trained model for: Deep Semantic Role Labeling: What Works and What's Next
This project helps natural language processing practitioners automatically identify who did what to whom in a sentence. You provide raw text, and it returns each sentence with its predicates (verbs or actions) and their arguments (the 'who' and 'what'). This is useful for researchers and developers working on deeper language understanding.
334 stars. No commits in the last 6 months.
Use this if you need to extract the semantic roles (agent, patient, instrument) for verbs in large volumes of text.
Not ideal if you're looking for a user-friendly application without needing to set up a Python development environment and command-line scripts.
Stars
334
Forks
78
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 23, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/luheng/deep_srl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
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
ChineseGLUE/ChineseGLUE
Language Understanding Evaluation benchmark for Chinese: datasets, baselines, pre-trained...