WenRichard/KBQA-BERT resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1470 stars · 345 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

learning-resource · maturity maintenance

nlp machine-learning search-engine parser artificial-intelligence machine-learning databases python cross-platform kbqa bert named-entity-recognition sentence-similarity knowledge-graph question-answering tensorflow nlpcc2017 chinese-nlp natural-language-processing linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="WenRichard/KBQA-BERT")