chakki-works/seqeval

Health v2 · maintenance only

Adoption not part of the score

1184 stars · 130 forks observed · 2026-08-28

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

seqeval is a Python library for evaluating sequence labeling tasks such as named-entity recognition, part-of-speech tagging, and semantic role labeling. It computes accuracy, precision, recall, and F1 scores with support for IOB1/IOB2/IOE1/IOE2/IOBES/BILOU schemes and a conlleval-compatible default mode.

Use cases

• evaluate NER model predictions with F1 score
• compute precision and recall for sequence labeling output
• generate a classification report for chunking tasks
• validate BIO-tagged predictions against conlleval behavior
• evaluate POS tagging or semantic role labeling performance
• score IOBES or BILOU scheme predictions in strict mode

When to choose

• you need standard NER/sequence-labeling metrics in Python
• you want results compatible with the Perl conlleval script
• you need strict scheme-aware evaluation for IOBES or BILOU tags

When to avoid

• you need general classification metrics without sequence structure
• you are not working with sequence labeling or chunking tasks

Facets

library · maturity stable

testing nlp machine-learning machine-learning deep-learning python sequence-labeling named-entity-recognition ner-evaluation conlleval pos-tagging iobes f1-score natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="chakki-works/seqeval")