Skip to content

The repository of our work "Learning Topic-Related Auxiliary Tasks for Topic-Oriented Dialogue Summarization"

Notifications You must be signed in to change notification settings

xiaolinAndy/TODS

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 

Repository files navigation

TODS

The repository of our work "Topic-Oriented Dialogue Summarization". The paper is under reviewing.

Instructions

1. Introduction

We propose a new dialogue summarization task named Topic-Oriented Dialogue Summarization (TODS). Given a dialogue and a specific topic, the task aims to generate a summary that covers the main content related to the given topic. To achieve this task, we propose three topic-related auxiliary tasks for TODS, including Topic Identification Task, Attention Restriction Task, and Topic Summary Distinguishing Task.

We experiment on two datasets (CSDS and DialogSum) by modifying them to adapt for TODS, and two baseline methods (BART-base and BART-large).

2. Necessary Resources

  • CSDS dataset: We put the processed CSDS-topic in data/CSDS/topic/.
  • DialogSum dataset: We put the processed DialogSum-topic in data/DialogSum/topic/.
  • Pretrained BART model:
    • bart-base Chinese for CSDS, available at here.
    • bart-large Chinese for CSDS, available at here.
    • bart-base English for DialogSum , available at here.
    • bart-large English for DialogSum , available at here.

3. Usage

Requirements

  • python == 3.8
  • pytorch == 1.8.1
  • files2rouge == 2.1.0
  • jieba == 0.42.1
  • numpy == 1.21.2
  • cytoolz == 0.11.2
  • nltk == 3.6.5
  • bert-score == 0.3.10
  • moverscore == 1.0.3
  • transformers == 4.4.1

Instructions

  1. Go to the models/ directory.
  2. Run the bash file run_CSDS.sh to train and test on CSDS-topic
  3. Run the bash file run_DialogSum.sh to train and test on DIALOGSUM-topic

4. Acknowledgement

The reference codes of the provided methods come from:

We thanks for all these researchers who have made their codes publicly available.

5. Citation

We will update the citation format after the paper is accepted.

If you have any issues, please contact with haitao.lin@nlpr.ia.ac.cn

About

The repository of our work "Learning Topic-Related Auxiliary Tasks for Topic-Oriented Dialogue Summarization"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published