yongzhuo/nlp_xiaojiang
自然语言处理（nlp），小姜机器人（闲聊检索式chatbot），BERT句向量-相似度（Sentence Similarity），XLNET句向量-相似度（text xlnet embedding），文本分类（Text classification）， 实体提取（ner，bert+bilstm+crf），数据增强（text augment, data enhance），同义句同义词生成，句子主干提取（mainpart），中文汉语短文本相似度，文本特征工程，keras-http-service调用
Implements multiple data augmentation strategies (back-translation, EDA, HMM-Markov, syntax-based generation) and hybrid retrieval chatbots combining fuzzy matching with BERT/XLNet sentence encodings for semantic similarity. Core NLP tasks use Keras-based architectures including BERT+BiLSTM+CRF for NER and multi-headed CNN/RNN variants (TextCNN, R-CNN, AVT-CNN) for text classification, leveraging pre-trained Chinese models from Google and Harbin Institute of Technology.
1,539 stars and 24 monthly downloads. No commits in the last 6 months. Available on PyPI.
Stars
1,539
Forks
391
Language
Python
License
MIT
Category
Last pushed
Sep 23, 2021
Monthly downloads
24
Commits (30d)
0
Dependencies
18
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/yongzhuo/nlp_xiaojiang"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
GaoQ1/rasa_nlu_gq
turn natural language into structured data(支持中文，自定义了N种模型，支持不同的场景和任务)
textgain/grasp
Essential NLP & ML, short & fast pure Python code
boat-group/fancy-nlp
NLP for human. A fast and easy-to-use natural language processing (NLP) toolkit, satisfying your...
changwookjun/nlp-paper
NLP Paper
NLP-kr/tensorflow-ml-nlp-tf2
텐서플로2와 머신러닝으로 시작하는 자연어처리 (로지스틱회귀부터 BERT와 GPT3까지) 실습자료