abisee/pointer-generator

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

2191 stars · 800 forks observed · 2026-08-28

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

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

library · maturity abandoned

machine-learning nlp deep-learning deep-learning machine-learning python text-summarization pointer-generator-network seq2seq attention tensorflow research-code abstractive-summarization natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="abisee/pointer-generator")