Natural language explanations of classifier behavior

Rodrigo Monteiro De Aquino; Fabio Cozman

doi:10.1109/AIKE.2019.00048

Natural language explanations of classifier behavior

Rodrigo Monteiro De Aquino, Fabio Cozman

Research output: Contribution to conference › Conference Paper

1 Scopus citations

Abstract

© 2019 IEEE. Tools that enhance interpretability of classifiers tend to focus on the knowledgeable data scientist. Here we propose techniques that generate textual explanations of the internal behavior of a given classifier, aiming at less technically proficient users of machine learning resources. Our approach has been positively evaluated by a group of users who received its textual output.

Original language	American English
Pages	239-242
Number of pages	4
DOIs	https://doi.org/10.1109/AIKE.2019.00048
State	Published - 1 Jun 2019
Externally published	Yes
Event	Proceedings - IEEE 2nd International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2019 - Duration: 1 Jun 2019 → …

Conference

Conference	Proceedings - IEEE 2nd International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2019
Period	1/06/19 → …

Access to Document

10.1109/AIKE.2019.00048

Cite this

@conference{9bfde9aa615246d28964e10bc0128093,

title = "Natural language explanations of classifier behavior",

abstract = "{\textcopyright} 2019 IEEE. Tools that enhance interpretability of classifiers tend to focus on the knowledgeable data scientist. Here we propose techniques that generate textual explanations of the internal behavior of a given classifier, aiming at less technically proficient users of machine learning resources. Our approach has been positively evaluated by a group of users who received its textual output.",

author = "{Monteiro De Aquino}, Rodrigo and Fabio Cozman",

year = "2019",

month = jun,

day = "1",

doi = "10.1109/AIKE.2019.00048",

language = "American English",

pages = "239--242",

note = "Proceedings - IEEE 2nd International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2019 ; Conference date: 01-06-2019",

}

TY - CONF

T1 - Natural language explanations of classifier behavior

AU - Monteiro De Aquino, Rodrigo

AU - Cozman, Fabio

PY - 2019/6/1

Y1 - 2019/6/1

N2 - © 2019 IEEE. Tools that enhance interpretability of classifiers tend to focus on the knowledgeable data scientist. Here we propose techniques that generate textual explanations of the internal behavior of a given classifier, aiming at less technically proficient users of machine learning resources. Our approach has been positively evaluated by a group of users who received its textual output.

AB - © 2019 IEEE. Tools that enhance interpretability of classifiers tend to focus on the knowledgeable data scientist. Here we propose techniques that generate textual explanations of the internal behavior of a given classifier, aiming at less technically proficient users of machine learning resources. Our approach has been positively evaluated by a group of users who received its textual output.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85071505579&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85071505579&origin=inward

U2 - 10.1109/AIKE.2019.00048

DO - 10.1109/AIKE.2019.00048

M3 - Conference Paper

SP - 239

EP - 242

T2 - Proceedings - IEEE 2nd International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2019

Y2 - 1 June 2019

ER -

Natural language explanations of classifier behavior

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this