searchableai/KitanaQA
KitanaQA: Adversarial training and data augmentation for neural question-answering models
This tool helps researchers and engineers improve the reliability and accuracy of AI models that answer questions from text. It takes your existing question-answering dataset and fine-tunes Transformer-based language models like BERT or ALBERT, outputting a more robust model that performs better in real-world situations with noisy inputs. It's designed for machine learning practitioners building or deploying question-answering systems.
No commits in the last 6 months. Available on PyPI.
Use this if you are building a question-answering system and need your AI model to be more stable and accurate when dealing with varied, real-world user questions and noisy text.
Not ideal if you are looking for a pre-trained, ready-to-use question-answering model without needing to fine-tune or enhance its robustness.
Stars
56
Forks
9
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 23, 2023
Commits (30d)
0
Dependencies
9
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/searchableai/KitanaQA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
dsfsi/textaugment
TextAugment: Text Augmentation Library
425776024/nlpcda
一键中文数据增强包 ； NLP数据增强、bert数据增强、EDA：pip install nlpcda
SanghunYun/UDA_pytorch
UDA(Unsupervised Data Augmentation) implemented by pytorch
google-research/uda
Unsupervised Data Augmentation (UDA)
KennethEnevoldsen/augmenty
Augmenty is an augmentation library based on spaCy for augmenting texts.