Skip to content

How Time Matters: Learning Time-Decay Attention for Contextual Spoken Language Understanding in Dialogue

Notifications You must be signed in to change notification settings

MiuLab/Time-Decay-SLU

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Time-Decay-Learning

How Time Matters: Learning Time-Decay Attention for Contextual Spoken Language Understanding in Dialogue

Reference

Main paper to be cited

@inproceedings{su2018how,
  title={How time matters: Learning Time-Decay Attention for Contextual Spoken Language Understanding in Dialogues},
    author={Shang-Yu Su, Pei-Chieh Yuan, and Yun-Nung Chen},
    booktitle={Proceedings of The 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
    year={2018}
}

Usage

  1. Put the DSTC4 data into some directory (e.g. /home/workspace/dstc4). Run the code parse_history.py to preprocess the data.

  2. Put the embedding files into some directory (e.g. /home/workspace/glove) Modify line 29 in the code slu_preprocess.py

  3. Run the code in the directory (row_*) with arguments like below:

    python slu.py \
    --target [ALL, Guide, Tourist]
    --level  [sentence, role]
    --attention [convex, linear, concave, universal]

About

How Time Matters: Learning Time-Decay Attention for Contextual Spoken Language Understanding in Dialogue

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages