# 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

Repository: https://github.com/yongzhuo/nlp_xiaojiang
Canonical: https://ross.abutalabs.com/products/nlp_xiaojiang
Homepage: https://blog.csdn.net/rensihui
Language: Python
License: MIT
License Family: permissive
Topics: chatbot, feature, data-augmentation, text-augment, enhance, chinese, nlp, distance, bert, xlnet, text-classification
Last push: 2021-09-23T05:44:27+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2703, "days_push": 1805, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1534, forks 391 (observed 2026-08-28T04:04:59.675117+00:00)

## What it is
A Chinese natural language processing toolkit covering retrieval-based chatbots, text classification, NER (BERT+BiLSTM+CRF), sentence embeddings with BERT/XLNet, and text data augmentation. It also provides text similarity feature engineering and a Keras-based HTTP service interface.

## Use cases
- augment chinese text data with back-translation and eda
- build a retrieval-based chinese chatbot
- compute sentence similarity with bert embeddings
- classify chinese short texts with bert and lstm
- extract named entities from chinese text
- generate synonym sentences for training data
- extract feature vectors from text with xlnet

## When to choose
- you need a collection of chinese nlp recipes (augmentation, similarity, ner, classification) in one place
- you want keras/tensorflow implementations of bert-based chinese models
- you need a simple retrieval chatbot over a QA corpus

## When to avoid
- you need actively maintained code or recent transformer support
- you need production-grade performance or pytorch-based tooling
- you work with non-chinese languages

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, machine-learning, chatbot, data-generation, search-engine
- domain: machine-learning, chatbots, localization
- platform: python, cross-platform
- tags: chinese-nlp, text-similarity, bert, xlnet, sentence-embedding, text-classification, named-entity-recognition, keras, retrieval-chatbot, text-augmentation, natural-language-processing

## Member repositories
- yongzhuo/nlp_xiaojiang (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:59.675117+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:31:13.786233+00:00, confidence not recorded.
  - readme: https://github.com/yongzhuo/nlp_xiaojiang (fetched 2026-08-28T04:04:59.675117+00:00, sha 33d6d06e344a)
  - homepage: https://blog.csdn.net/rensihui (fetched 2026-08-29T11:33:21.744750+00:00, sha 4c771860b30f)
  - registry_pypi: https://pypi.org/pypi/nlp_xiaojiang/json (fetched 2026-08-29T11:33:21.754179+00:00, sha 84fa998c2c37)
- Data as of 2026-08-30T08:39:29.467469+00:00.