SALT-NLP/DADA
This is the oficial repository for "DADA: Dialect Adaptation via Dynamic Aggregation of Linguistic Rules".
This project helps natural language processing (NLP) practitioners and researchers adapt large language models (LLMs) to understand and process various English dialects beyond Standard American English. It takes an existing LLM and improves its performance on diverse dialectal texts. The result is a more robust LLM capable of accurately handling different English variants, which is particularly useful for tasks involving global communication or diverse user bases.
No commits in the last 6 months.
Use this if you need to improve the accuracy and robustness of your language models when dealing with text data that includes different English dialects.
Not ideal if your language model only ever processes Standard American English, or if you need to adapt to non-English languages.
Stars
8
Forks
—
Language
Python
License
—
Category
Last pushed
Oct 11, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/SALT-NLP/DADA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
princeton-nlp/SimCSE
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
n-waves/multifit
The code to reproduce results from paper "MultiFiT: Efficient Multi-lingual Language Model...
yxuansu/SimCTG
[NeurIPS'22 Spotlight] A Contrastive Framework for Neural Text Generation
alibaba-edu/simple-effective-text-matching
Source code of the ACL2019 paper "Simple and Effective Text Matching with Richer Alignment Features".
Shark-NLP/OpenICL
OpenICL is an open-source framework to facilitate research, development, and prototyping of...