lukasruff/CVDD-PyTorch
A PyTorch implementation of Context Vector Data Description (CVDD), a method for Anomaly Detection on text.
This project helps identify unusual or 'anomalous' sentences or phrases within a large collection of text. It takes raw text data as input and highlights specific segments that don't fit the dominant themes or concepts. It's designed for data scientists, researchers, or analysts who need to spot oddities in text without having to manually label data.
No commits in the last 6 months.
Use this if you need to automatically find strange or out-of-place sentences in a large, unlabeled text dataset, like identifying unusual customer feedback or outlier news articles.
Not ideal if you already have labeled examples of what an anomaly looks like, or if your data is not text-based.
Stars
72
Forks
21
Language
Python
License
MIT
Last pushed
Jun 21, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/lukasruff/CVDD-PyTorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
gaussic/text-classification-cnn-rnn
CNN-RNN中文文本分类，基于TensorFlow
ShawnyXiao/TextClassification-Keras
Text classification models implemented in Keras, including: FastText, TextCNN, TextRNN,...
prakashpandey9/Text-Classification-Pytorch
Text classification using deep learning models in Pytorch
TobiasLee/Text-Classification
Implementation of papers for text classification task on DBpedia
FreedomIntelligence/TextClassificationBenchmark
A Benchmark of Text Classification in PyTorch