[“Explainable AI Research”]

Welcome! You can find research assets of our Explainable AI (XAI) Research Project in this website including past demos, papers, survey, and tutorials.

List of Contributors (in alphabetical order)

Ranit Aharonov - IBM Research
Marina Danilevsky - IBM Research
Shipi Dhanorkar - Pennsylvania State University
Yannis Katsis - IBM Research
Ban Kawas - Facebook AI Research
Yunyao Li - IBM Research
Erick Oduor - IBM
Lucian Popa - IBM Research
Kun Qian - Amazon
Prithviraj Sen - IBM Research
Chritine T Wolf - Independent Researcher
Anbang Xu - IBM Research

Demos

XNLP: A Living Survey for XAI Research in Natural Language Processing
Kun Qian, Marina Danilevsky, Yannis Katsis, Ban Kawas, Erick Oduor, Lucian Popa, Yunyao Li
(IUI 2021)
Paper, Website

XAIT: An Interactive Website for Explainable AI for Text.
Eno Oduor, Kun Qian, Yunyao Li, Lucian Popa
(IUI 2020)
Paper

Survey

A Survey of the State of Explainable AI for Natural Language Processing
Marina Danilevsky, Kun Qian, Ranit Aharonov, Yannis Katasis, Ban Kawas, Prithviraj Sen
(AACL-IJCNLP 2020)
Paper, Companion Website

Tutorials

Explainability for Natural Language Processing.
Marina Danilevsky, Shipi Dhanorkar, Yunyao Li, Lucian Popa, Kun Qian, Anbang Xu
(KDD 2021)
Website

Explainability for Natural Language Processing.
Shipi Dhanorkar, Yunyao Li, Lucian Popa, Kun Qian, Christine T Wolf, Anbang Xu
(AACL-IJCNLP 2020)
Video-Recording, Slides

Research Paper

Who needs to know what, when?: Broadening the Explainable AI (XAI) Design Space by Looking at Explanations Across the AI Lifecycle
Shipi Dhanorkar, Christine T Wolf, Kun Qian, Anbang Xu, Lucian Popa, Yunyao Li
(ACM DIS 2021, to appear)

Cite our work

If you find our work useful, please cite our work

KDD 2021 tutorial (Explainability for Natural Language Processing)

@inproceedings{danilevsky2021explainability,
title={Explainability for Natural Language Processing},
author={Danilevsky, Marina and Dhanorkar, Shipi and Li, Yunyao and Popa, Lucian and Qian, Kun and Xu, Anbang},
booktitle={Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery \& Data Mining},
pages={4033--4034},
year={2021}
}

IUI 2021 demo (XNLP website)

@inproceedings{10.1145/3397482.3450728,
  author = {Qian, Kun and Danilevsky, Marina and Katsis, Yannis and Kawas, Ban and Oduor, Erick and Popa, Lucian and Li, Yunyao},
  title = {XNLP: A Living Survey for XAI Research in Natural Language Processing},
  year = {2021},
  isbn = {9781450380188},
  publisher = {Association for Computing Machinery},
  doi = {10.1145/3397482.3450728},
  booktitle = {26th International Conference on Intelligent User Interfaces},
  pages = {78–80},
  numpages = {3},
  series = {IUI '21}
}

IUI 2020 demo

@inproceedings{10.1145/3379336.3381468,
  author = {Oduor, Erick and Qian, Kun and Li, Yunyao and Popa, Lucian},
  title = {XAIT: An Interactive Website for Explainable AI for Text},
  year = {2020},
  isbn = {9781450375139},
  publisher = {Association for Computing Machinery},
  address = {New York, NY, USA},
  url = {https://doi.org/10.1145/3379336.3381468},
  doi = {10.1145/3379336.3381468},
  booktitle = {Proceedings of the 25th International Conference on Intelligent User Interfaces Companion},
  pages = {120–121},
  numpages = {2},
  keywords = {Natural Language Processing, Explainable AI},
  location = {Cagliari, Italy},
  series = {IUI ’20}
}

Survey Paper:

@inproceedings{danilevsky-etal-2020-survey,
  title = "A Survey of the State of Explainable {AI} for Natural Language Processing",
  author = "Danilevsky, Marina  and
    Qian, Kun  and
    Aharonov, Ranit  and
    Katsis, Yannis  and
    Kawas, Ban  and
    Sen, Prithviraj",
  booktitle = "Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing",
  year = "2020",
  publisher = "Association for Computational Linguistics",
  pages = "447--459"
}