# LeeSureman/Flat-Lattice-Transformer

code for ACL 2020 paper: FLAT: Chinese NER Using Flat-Lattice Transformer

Repository: https://github.com/LeeSureman/Flat-Lattice-Transformer
Canonical: https://ross.abutalabs.com/products/flat-lattice-transformer
Language: Python
License Family: other
Last push: 2022-05-10T05:18:21+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": 2317, "days_push": 1576, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1003, forks 170 (observed 2026-09-03T02:15:06.504271+00:00)

## What it is
Reference implementation of the ACL 2020 paper FLAT: Chinese NER Using Flat-Lattice Transformer, built on PyTorch and FastNLP. It trains flat-lattice transformer models for Chinese named entity recognition on datasets like OntoNotes, MSRA, Weibo, and Resume, with optional BERT integration.

## Use cases
- run Chinese named entity recognition with a flat-lattice transformer
- reproduce FLAT NER results from the ACL 2020 paper
- train a Chinese NER model on MSRA or OntoNotes
- compare lattice-based transformer NER against BERT baselines
- experiment with character and word lattice embeddings for Chinese NER

## When to choose
- you need a strong research-grade Chinese NER model with lattice structure
- you want to reproduce or extend the FLAT ACL 2020 paper
- you work with PyTorch and FastNLP for Chinese sequence labeling

## When to avoid
- you need a production-ready NER service with an API
- you want multilingual or non-Chinese NER out of the box
- you need actively maintained code with a license and recent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, machine-learning, deep-learning
- domain: machine-learning, deep-learning
- platform: python
- tags: named-entity-recognition, chinese-nlp, transformer, lattice-structure, research-code, acl-2020, pytorch, natural-language-processing

## Member repositories
- LeeSureman/Flat-Lattice-Transformer (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-09-03T02:15:06.504271+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 2026-08-30T07:13:48.437636+00:00, confidence not recorded.
  - readme: https://github.com/LeeSureman/Flat-Lattice-Transformer (fetched 2026-09-03T02:15:06.504271+00:00, sha 2f50e2f13d06)
- Data as of 2026-08-30T08:39:29.467469+00:00.