Skip to content

Code for WWW 2023 paper "HISum: Hyperbolic Interaction Model for Extractive Multi-Document Summarization".

Notifications You must be signed in to change notification settings

MySong7NLPer/HISum

Repository files navigation

HISum

This repository provides the code of the paper HISum: Hyperbolic Interaction Model for Extractive Multi-Document Summarization (WWW2023).

Data and Checkpoints.

Dependencies

  • Python 3.7
  • PyTorch 1.4.0
  • fastNLP 0.5.0
  • pyrouge 0.1.3
    • You should fill your ROUGE path in metrics.py line 20 before running our code.
  • rouge 1.0.0
    • Used in the validation phase.
  • transformers 2.5.1

All code only supports running on Linux.

CONTACT

For any question, feel free to create an issue, and we will try our best to solve.
If the problem is more urgent, you can send an email to me at the same time (I check email almost everyday).

NAME: Mingyang Song
EMAIL: mingyang.song@bjtu.edu.cn

Our implementation is built on the source code from MatchSum. Thanks for their work.

About

Code for WWW 2023 paper "HISum: Hyperbolic Interaction Model for Extractive Multi-Document Summarization".

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published