rajaswa/indic-syntax-evaluation
Vyākarana: A Colorless Green Benchmark for Syntactic Evaluation in Indic Languages
This project offers a specialized benchmark dataset, "Vyākarana," to evaluate how well large language models understand the grammatical structure (syntax) of Indic languages like Hindi and Tamil. It takes various language models as input and produces detailed scores on their ability to perform tasks like identifying parts of speech, understanding grammatical case, and subject-verb agreement. Researchers and developers working on natural language processing for Indic languages would use this to gauge and improve their models' syntactic comprehension.
No commits in the last 6 months.
Use this if you are a researcher or developer who needs to rigorously test the syntactic capabilities of multilingual or Indic language models.
Not ideal if you are looking for an off-the-shelf tool for general text analysis or translation in Indic languages, rather than model evaluation.
Stars
15
Forks
2
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 28, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/rajaswa/indic-syntax-evaluation"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LoicGrobol/zeldarose
Train transformer-based models.
CPJKU/wechsel
Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of...
yuanzhoulvpi2017/zero_nlp
中文nlp解决方案(大模型、数据、模型、训练、推理)
minggnim/nlp-models
A repository for training transformer based models
IntelLabs/nlp-architect
A model library for exploring state-of-the-art deep learning topologies and techniques for...