# dmmiller612/bert-extractive-summarizer

Easy to use extractive text summarization with BERT

Repository: https://github.com/dmmiller612/bert-extractive-summarizer
Canonical: https://ross.abutalabs.com/products/bert-extractive-summarizer
Language: Python
License: MIT
License Family: permissive
Topics: bert, extractive-summarization, pytorch, coreference
Last push: 2023-06-12T21:51:00+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2671, "days_push": 1178, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1453, forks 306 (observed 2026-08-28T04:04:46.573134+00:00)

## What it is
A Python library for extractive text summarization using BERT embeddings via HuggingFace transformers. It embeds sentences, clusters them, and selects sentences closest to cluster centroids, with optional coreference resolution.

## Use cases
- summarize long articles with python
- extract key sentences from a document
- summarize lecture transcripts
- get a short summary of text using BERT
- condense news articles into a few sentences
- summarize text with sentence transformers

## When to choose
- you need extractive (not abstractive) summarization in Python
- you want a simple pip-installable summarizer with BERT or SBERT embeddings
- you need GPU-accelerated summarization with configurable sentence counts

## When to avoid
- you need abstractive summaries that rewrite text
- you need a production service with active maintenance
- you cannot run transformer models due to compute constraints

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, machine-learning
- domain: machine-learning
- platform: python
- tags: bert, extractive-summarization, pytorch, coreference, sentence-embeddings, natural-language-processing

## Member repositories
- dmmiller612/bert-extractive-summarizer (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:46.573134+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 2026-08-30T04:35:44.797040+00:00, confidence not recorded.
  - readme: https://github.com/dmmiller612/bert-extractive-summarizer (fetched 2026-08-28T04:04:46.573134+00:00, sha 150c06583bb0)
  - registry_pypi: https://pypi.org/pypi/bert-extractive-summarizer/json (fetched 2026-08-29T11:44:59.362624+00:00, sha 7a1fe7130272)
- Data as of 2026-08-30T08:39:29.467469+00:00.