Baike.dev
All toolsOnline toolsAI codingTrendingOpen sourceNewsSubmit
Log in
< Back to tools
N

neural-summ-cnndm-pytorch

> 编程语言
Open source

Neural abstractive summarization (seq2seq + copy (or pointer network) + coverage) in pytorch on CNN/Daily Mail

200 stars0 likes0 views
WebsiteGitHub

About

Neural abstractive summarization (seq2seq + copy (or pointer network) + coverage) in pytorch on CNN/Daily Mail

Abstractive Summarization on CNN-DailyMail

Results

Model-1: attention-seq2seq

Model-2: attention-seq2seq + copy

GRU (NLL loss + norm-clip=5):
…

Model-3: attention-seq2seq + coverage

GRU (NLL loss + norm-clip=5):
…

Model-4: attention-seq2seq + copy + coverage

GRU (NLL loss + norm-clip=5):
…
GRU (avg NLL loss + norm-clip=2):
…
LSTM-v1 (avg NLL loss + norm-clip=2): Pointer-Generator in ACL'17
…
LSTM-v2 (avg NLL loss + norm-clip=2):
…

How to run:

  • Python 3.7, Pytorch 0.4+
  • Download the processed dataset from: https://drive.google.com/drive/folders/0BxUmZA_RBdXnRHk1LUY4YTd2R0U?resourcekey=0-Sob5ZkyzF4T64EiZOBvD8g&usp=sharing , or you can download the original FINISHED_FILES from: https://github.com/JafferWilson/Process-Data-of-CNN-DailyMail , and process by yourself.
  • Modify the path in prepare_data.py then run it: python prepare_data.py
  • Training: python -u main.py | tee train.log
  • Tuning: modify main.py: is_predicting=true and model_selection=true, then run "bash tuning_deepmind.sh | tee tune.log"
  • Testing: modify main.py: is_predicting=true and model_selection=false, then run "python main.py you-best-model (say cnndm.s2s.gpu4.epoch7.1)", go to "./deepmind/result/" and run $ROUGE$ myROUGE_Config.xml C, you will get the results.
  • The Perl Rouge package is enough, I did not use pyrouge.

Issues· 4 open

View all issuesOpen on GitHub

No open issues yet, or sync has not completed.

> Tags

Pythonabstractive-summarizationcnn-dailymailpytorch

No comments yet. Be the first to share.

> Details

PublishedAug 1, 2026
UpdatedSep 18, 2026
Category编程语言
PricingOpen source

> Related tools

T
TypeScript
JavaScript 的超集,为前端与全栈提供静态类型
P
Python
通用编程语言,广泛用于 Web、数据与 AI
G
Go
Google 推出的简洁高效系统语言