Natural Language Explanations of Classifier Behavior

被引：0

作者：

de Aquino, Rodrigo Monteiro ^{[1
]}

Cozman, Fabio Gagliardi ^{[1
]}

机构：

[1] Univ Sao Paulo, Escola Politecn, Sao Paulo, SP, Brazil

来源：

2019 IEEE SECOND INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND KNOWLEDGE ENGINEERING (AIKE) | 2019年

关键词：

machine learning; interpretability; transparency;

D O I：

10.1109/AIKE.2019.00048

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：239 / 242

页数：4

共 50 条

[41] Zero-Shot Classification by Logical Reasoning on Natural Language Explanations
Han, Chi
Pei, Hengzhi
Du, Xinya
Ji, Heng
FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2023), 2023, : 8967 - 8981
[42] Supervising Model Attention with Human Explanations for Robust Natural Language Inference
Stacey, Joe
Belinkov, Yonatan
Rei, Marek
THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 11349 - 11357
[43] Rationalization: A Neural Machine Translation Approach to Generating Natural Language Explanations
Ehsan, Upol
Harrison, Brent
Chan, Larry
Riedl, Mark O.
PROCEEDINGS OF THE 2018 AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY (AIES'18), 2018, : 81 - 87
[44] e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks
Kayser, Maxime
Camburu, Oana-Maria
Salewski, Leonard
Emde, Cornelius
Do, Virginie
Akata, Zeynep
Lukasiewicz, Thomas
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 1224 - 1234
[45] NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks
Sammani, Fawaz
Mukherjee, Tanmoy
Deligiannis, Nikos
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2022, : 8312 - 8322
[46] Toward Generating Natural-Language Explanations of Modal-Logic Proofs
Giancola, Mike
Bringsjord, Selmer
Govindarajulu, Naveen Sundar
ARTIFICIAL GENERAL INTELLIGENCE, AGI 2022, 2023, 13539 : 220 - 230
[47] Semi-automated classifier adaptation for natural language call routing
Witt, Silke M.
12TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011 (INTERSPEECH 2011), VOLS 1-5, 2011, : 1352 - 1355
[48] Crime as natural event? Biological explanations in German-language criminology textbooks
Fuchs, Walter
KRIMINOLOGISCHES JOURNAL, 2013, 45 (01): : 25 - 43
[49] Shortcut Learning Explanations for Deep Natural Language Processing: A Survey on Dataset Biases
Dogra, Varun
Verma, Sahil
Kavita
Wozniak, Marcin
Shafi, Jana
Ijaz, Muhammad Fazal
IEEE ACCESS, 2024, 12 : 26183 - 26195
[50] TextFocus: Assessing the Faithfulness of Feature Attribution Methods Explanations in Natural Language Processing
Mariotti, Ettore
Arias-Duart, Anna
Cafagna, Michele
Gatt, Albert
Garcia-Gasulla, Dario
Alonso-Moral, Jose Maria
IEEE ACCESS, 2024, 12 : 138870 - 138880

← 1 2 3 4 5 →