blmoistawinde/HarvestText

Health v2 · maintenance only

Adoption not part of the score

2628 stars · 340 forks observed · 2026-08-28

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

HarvestText is a Python library for Chinese text mining and preprocessing using unsupervised or weakly supervised methods. It integrates domain knowledge such as entity types and aliases to support tasks like entity linking, sentiment analysis, new word discovery, keyword extraction, dependency parsing, and simple knowledge graph QA.

Use cases

• find new words and slang in Chinese social media text
• link entity aliases and abbreviations to canonical names
• analyze sentiment of comments and posts
• extract keywords and summarize documents
• build a social network from a novel by tracking character co-occurrence
• extract fact triples from sentences via dependency parsing
• clean URLs, emails, and special symbols from web text
• segment long unsegmented text automatically

When to choose

• you need lightweight unsupervised Chinese NLP preprocessing without training data
• you want to combine domain dictionaries and entity aliases with segmentation
• you are doing exploratory analysis of Chinese novels, forums, or specialized literature

When to avoid

• you need state-of-the-art supervised NER or parsing accuracy
• your primary language is English (support is limited)
• you need a production-grade knowledge graph QA system

Facets

library · maturity maintenance

nlp parser search-engine data-science text-editors data-science python cross-platform chinese-nlp entity-linking new-word-discovery sentiment-analysis text-summarization keyword-extraction dependency-parsing unsupervised text-cleaning knowledge-extraction natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="blmoistawinde/HarvestText")