Skip to content
/ RSVP Public

Official Implementation for RSVP: Customer Intent Detection via Agent Response Contrastive and Generative Pre-Training (EMNLP'23)

License

Notifications You must be signed in to change notification settings

tommytyc/RSVP

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Official implementation for our EMNLP 2023 Findings paper "RSVP: Customer Intent Detection via Agent Response Contrastive and Generative Pre-Training".

Setup

  • Build environment
pip3 install requirements.txt
  • Put data in data/

Run

  • Overall running command
python3 RSVP.py --train_path [train_data_path] --dev_path [dev/valid_data_path] --test_path [test_data_path] --label_map_path [label_map_path] --task [task_name] 
  • For example, TwACS
python3 RSVP.py --train_path data/airlines_train.csv --dev_path data/airlines_valid.csv --test_path data/airlines_test.csv --label_map_path data/airline_label_map.pkl --task airline
  • The task include airline, woz, and sgd.

About

Official Implementation for RSVP: Customer Intent Detection via Agent Response Contrastive and Generative Pre-Training (EMNLP'23)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages