A Survey of Explainable AI Terminology

Miruna A. Clinciu; Helen F. Hastie

doi:10.18653/v1/W19-8403

A Survey of Explainable AI Terminology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The field of Explainable Artificial Intelligence attempts to solve the problem of algorithmic opacity. Many terms and notions have been introduced recently to define Explainable AI, however, these terms seem to be used interchangeably, which is leading to confusion in this rapidly expanding field. As a solution to overcome this problem, we present an analysis of the existing research literature and examine how key terms, such as transparency, intelligibility, interpretability, and explainability are referred to and in what context. This paper, thus, moves towards a standard terminology for Explainable AI.

Original language	English
Title of host publication	Proceedings of the 1st Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence
Publisher	Association for Computational Linguistics
Pages	8-13
Number of pages	6
ISBN (Print)	9781950737703
DOIs	https://doi.org/10.18653/v1/W19-8403
Publication status	Published - 29 Oct 2019
Event	1st Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence 2019 - Tokyo, Japan Duration: 29 Oct 2019 → … Conference number: 1 https://sites.google.com/view/nl4xai2019/

Workshop

Workshop	1st Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence 2019
Abbreviated title	NL4XAI 2019
Country/Territory	Japan
City	Tokyo
Period	29/10/19 → …
Internet address	https://sites.google.com/view/nl4xai2019/

Keywords / Materials (for Non-textual outputs)

explainable AI
black-box
NLG
theoretical issues
transparency
intelligibility
interpretability
explainability

Access to Document

10.18653/v1/W19-8403Licence: Creative Commons: Attribution (CC-BY)

A Survey of_CLINCIU_DOA01102019_VOR_CC BYFinal published version, 154 KBLicence: Creative Commons: Attribution (CC-BY)

https://aclanthology.org/W19-8403/Licence: All Rights Reserved

Cite this

@inproceedings{b3b83b083eac44049b61afaafdef0c65,

title = "A Survey of Explainable AI Terminology",

abstract = "The field of Explainable Artificial Intelligence attempts to solve the problem of algorithmic opacity. Many terms and notions have been introduced recently to define Explainable AI, however, these terms seem to be used interchangeably, which is leading to confusion in this rapidly expanding field. As a solution to overcome this problem, we present an analysis of the existing research literature and examine how key terms, such as transparency, intelligibility, interpretability, and explainability are referred to and in what context. This paper, thus, moves towards a standard terminology for Explainable AI.",

keywords = "explainable AI, black-box, NLG, theoretical issues, transparency, intelligibility, interpretability, explainability",

author = "Clinciu, {Miruna A.} and Hastie, {Helen F.}",

year = "2019",

month = oct,

day = "29",

doi = "10.18653/v1/W19-8403",

language = "English",

isbn = "9781950737703",

pages = "8--13",

booktitle = "Proceedings of the 1st Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence",

publisher = "Association for Computational Linguistics",

note = "1st Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence 2019, NL4XAI 2019 ; Conference date: 29-10-2019",

url = "https://sites.google.com/view/nl4xai2019/",

}

Clinciu, MA & Hastie, HF 2019, A Survey of Explainable AI Terminology. in Proceedings of the 1st Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence. Association for Computational Linguistics, pp. 8-13, 1st Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence 2019, Tokyo, Japan, 29/10/19. https://doi.org/10.18653/v1/W19-8403

TY - GEN

T1 - A Survey of Explainable AI Terminology

AU - Clinciu, Miruna A.

AU - Hastie, Helen F.

N1 - Conference code: 1

PY - 2019/10/29

Y1 - 2019/10/29

N2 - The field of Explainable Artificial Intelligence attempts to solve the problem of algorithmic opacity. Many terms and notions have been introduced recently to define Explainable AI, however, these terms seem to be used interchangeably, which is leading to confusion in this rapidly expanding field. As a solution to overcome this problem, we present an analysis of the existing research literature and examine how key terms, such as transparency, intelligibility, interpretability, and explainability are referred to and in what context. This paper, thus, moves towards a standard terminology for Explainable AI.

AB - The field of Explainable Artificial Intelligence attempts to solve the problem of algorithmic opacity. Many terms and notions have been introduced recently to define Explainable AI, however, these terms seem to be used interchangeably, which is leading to confusion in this rapidly expanding field. As a solution to overcome this problem, we present an analysis of the existing research literature and examine how key terms, such as transparency, intelligibility, interpretability, and explainability are referred to and in what context. This paper, thus, moves towards a standard terminology for Explainable AI.

KW - explainable AI

KW - black-box

KW - NLG

KW - theoretical issues

KW - transparency

KW - intelligibility

KW - interpretability

KW - explainability

U2 - 10.18653/v1/W19-8403

DO - 10.18653/v1/W19-8403

M3 - Conference contribution

SN - 9781950737703

SP - 8

EP - 13

BT - Proceedings of the 1st Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence

PB - Association for Computational Linguistics

T2 - 1st Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence 2019

Y2 - 29 October 2019

ER -

A Survey of Explainable AI Terminology

Abstract

Workshop

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Cite this