# abisee/pointer-generator

Code for the ACL 2017 paper "Get To The Point: Summarization with Pointer-Generator Networks"

Repository: https://github.com/abisee/pointer-generator
Canonical: https://ross.abutalabs.com/products/pointer-generator
Language: Python
License: NOASSERTION
License Family: other
Last push: 2022-06-16T22:05:16+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3420, "days_push": 1539, "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 2191, forks 800 (observed 2026-08-28T04:06:24.184499+00:00)

## What it is
Reference implementation of the pointer-generator network from the ACL 2017 paper 'Get To The Point: Summarization with Pointer-Generator Networks', built on TensorFlow. It provides training and decoding code for abstractive text summarization, plus pretrained models and CNN/Daily Mail data instructions.

## Use cases
- reproduce abstractive summarization results from the pointer-generator paper
- train a seq2seq summarization model on CNN/Daily Mail
- study how pointer networks copy words from source text
- run beam search decoding for text summarization
- use a pretrained summarization model for experiments
- learn how attention-based summarization models are implemented

## When to choose
- you need the canonical implementation of the pointer-generator architecture for research or teaching
- you want to reproduce or extend a classic ACL 2017 summarization baseline
- you are okay working with older TensorFlow 1.x code

## When to avoid
- you need a maintained library compatible with modern TensorFlow or PyTorch
- you want production-ready summarization with state-of-the-art quality
- you prefer transformer-based summarization models

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, nlp, deep-learning
- domain: deep-learning, machine-learning
- platform: python
- tags: text-summarization, pointer-generator-network, seq2seq, attention, tensorflow, research-code, abstractive-summarization, natural-language-processing

## Member repositories
- abisee/pointer-generator (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:24.184499+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 2026-08-30T02:47:28.734890+00:00, confidence not recorded.
  - readme: https://github.com/abisee/pointer-generator (fetched 2026-08-28T04:06:24.184499+00:00, sha a9b662c68b5e)
- Data as of 2026-08-30T08:39:29.467469+00:00.