atulkum/pointer_summarizer

pytorch implementation of "Get To The Point: Summarization with Pointer-Generator Networks"

51
/ 100
Established

Implements a hybrid seq2seq-attention architecture that combines copy mechanisms (pointer networks) with vocabulary generation, enabling the model to both reproduce source text and generate novel words. Includes optional coverage loss to penalize repetitive attention patterns, improving coherence on abstractive summarization tasks. Trainable end-to-end on CNN/DailyMail datasets with beam search decoding and ROUGE evaluation metrics built in.

915 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

915

Forks

238

Language

Python

License

Apache-2.0

Last pushed

Jan 23, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/atulkum/pointer_summarizer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.