/peach

Primary LanguageJupyter Notebook

PEACH: Pretrained-embedding Explanation Across Contextual and Hierarchical Structure

The paper is accepted at IJCAI 2024. The detailed documentation with examples for applying the code will be shared later.

Feiqi Cao*, Soyeon Caren Han*, Hyunsuk Chung. (2024, August).
PEACH: Pretrained-embedding Explanation Across Contextual and Hierarchical Structure

The 33rd International Joint Conference on Artificial Intelligence
(IJCAI 2024).
[paper]|[appendix][presentation]

Citation

@inproceedings{ijcai2024p686,
  title     = {PEACH: Pretrained-Embedding Explanation across Contextual and Hierarchical Structure},
  author    = {Cao, Feiqi and Han, Soyeon Caren and Chung, Hyunsuk},
  booktitle = {Proceedings of the Thirty-Third International Joint Conference on
               Artificial Intelligence, {IJCAI-24}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Kate Larson},
  pages     = {6207--6215},
  year      = {2024},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2024/686},
  url       = {https://doi.org/10.24963/ijcai.2024/686},
}

Qualitative Examples

We visualised the global and local explanation tree for the text classification tasks. Here are some examples. For more details please refer to our paper.

  • Global example:

  • Local examples: