# WenRichard/KBQA-BERT

基于知识图谱的问答系统，BERT做命名实体识别和句子相似度，分为online和outline模式

Repository: https://github.com/WenRichard/KBQA-BERT
Canonical: https://ross.abutalabs.com/products/kbqa-bert
Language: Python
License: MIT
License Family: permissive
Topics: bert, knowledge-graph, sentence-similarity, nlpcc2017
Last push: 2021-12-16T12:05:22+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": 2693, "days_push": 1721, "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 1470, forks 345 (observed 2026-08-28T04:04:49.155216+00:00)

## What it is
A knowledge base question answering (KBQA) system that uses BERT for named entity recognition and sentence similarity, built in Python with TensorFlow. It combines an NER module and a similarity module into a QA pipeline, with online and offline prediction modes, using NLPCC 2016/2017 datasets and a MySQL-backed knowledge graph.

## Use cases
- build a question answering system over a knowledge graph
- train BERT for Chinese named entity recognition
- compute sentence similarity with BERT
- learn how to combine NER and semantic matching for KBQA
- run question answering on NLPCC 2017 data

## When to choose
- studying KBQA pipelines with BERT as a reference implementation
- needing a working example of BERT-based NER with LSTM-CRF
- replicating NLPCC knowledge base question answering experiments

## When to avoid
- production deployments needing maintained dependencies (TensorFlow 1.13, Python 3.6)
- multilingual or non-Chinese question answering
- projects requiring active support or recent updates

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: nlp, machine-learning, search-engine, parser
- domain: artificial-intelligence, machine-learning, databases
- platform: python, cross-platform
- tags: kbqa, bert, named-entity-recognition, sentence-similarity, knowledge-graph, question-answering, tensorflow, nlpcc2017, chinese-nlp, natural-language-processing, linux

## Member repositories
- WenRichard/KBQA-BERT (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:49.155216+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 2026-08-30T04:34:48.145441+00:00, confidence not recorded.
  - readme: https://github.com/WenRichard/KBQA-BERT (fetched 2026-08-28T04:04:49.155216+00:00, sha 14207ea53efb)
- Data as of 2026-08-30T08:39:29.467469+00:00.