prajjwal1/generalize_lm_nli
Code for the paper EMNLP 2021 workshop paper "Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics"
When developing Natural Language Inference (NLI) models, it's common for them to rely on simple shortcuts rather than truly understanding the text. This project offers tools and pre-trained models for researchers to test and improve how well their NLI models generalize. You can input text pairs with labels (entailment, contradiction, neutral) and apply various training strategies to output models that are more robust.
No commits in the last 6 months.
Use this if you are an NLP researcher or data scientist focused on developing and evaluating the generalization capabilities of NLI models, particularly in avoiding dataset-specific heuristics.
Not ideal if you are looking for a plug-and-play NLI solution for immediate production use without deep experimentation into model generalization.
Stars
34
Forks
3
Language
Jupyter Notebook
License
GPL-3.0
Category
Last pushed
Jan 15, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/prajjwal1/generalize_lm_nli"
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...