Towards making NLG a voice for interpretable Machine Learning

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Downloads (Pure)

Abstract

This paper presents a study to understand the issues related to using NLG to humanise explanations from a popular interpretable machine learning framework
called LIME. Our study shows that selfreported rating of NLG explanation was
higher than that for a non-NLG explanation. However, when tested for comprehension, the results were not as clearcut showing the need for performing more studies to uncover the factors responsible for high-quality NLG explanations.
Original languageEnglish
Title of host publicationProceedings of The 11th International Natural Language Generation Conference
EditorsEmiel Krahmer, Albert Gatt, Martijn Goudbeek
PublisherAssociation for Computational Linguistics (ACL)
Pages177-182
Number of pages6
ISBN (Print)9781948087865
Publication statusPublished - 30 Nov 2018
Event11th International Conference on Natural Language Generation (INLG 2018) - Tilburg University, Tilburg, Netherlands
Duration: 5 Nov 20188 Nov 2018

Conference

Conference11th International Conference on Natural Language Generation (INLG 2018)
CountryNetherlands
CityTilburg
Period5/11/188/11/18

Fingerprint

Learning systems

Cite this

Forrest, J., Sripada, S., Pang, W., & Coghill, G. (2018). Towards making NLG a voice for interpretable Machine Learning. In E. Krahmer, A. Gatt, & M. Goudbeek (Eds.), Proceedings of The 11th International Natural Language Generation Conference (pp. 177-182). [W18-6522] Association for Computational Linguistics (ACL).

Towards making NLG a voice for interpretable Machine Learning. / Forrest, James; Sripada, Somayajulu; Pang, Wei; Coghill, George.

Proceedings of The 11th International Natural Language Generation Conference. ed. / Emiel Krahmer; Albert Gatt; Martijn Goudbeek. Association for Computational Linguistics (ACL), 2018. p. 177-182 W18-6522.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Forrest, J, Sripada, S, Pang, W & Coghill, G 2018, Towards making NLG a voice for interpretable Machine Learning. in E Krahmer, A Gatt & M Goudbeek (eds), Proceedings of The 11th International Natural Language Generation Conference., W18-6522, Association for Computational Linguistics (ACL), pp. 177-182, 11th International Conference on Natural Language Generation (INLG 2018) , Tilburg, Netherlands, 5/11/18.
Forrest J, Sripada S, Pang W, Coghill G. Towards making NLG a voice for interpretable Machine Learning. In Krahmer E, Gatt A, Goudbeek M, editors, Proceedings of The 11th International Natural Language Generation Conference. Association for Computational Linguistics (ACL). 2018. p. 177-182. W18-6522
Forrest, James ; Sripada, Somayajulu ; Pang, Wei ; Coghill, George. / Towards making NLG a voice for interpretable Machine Learning. Proceedings of The 11th International Natural Language Generation Conference. editor / Emiel Krahmer ; Albert Gatt ; Martijn Goudbeek. Association for Computational Linguistics (ACL), 2018. pp. 177-182
@inproceedings{52145cd28289471094f6a219594e2e60,
title = "Towards making NLG a voice for interpretable Machine Learning",
abstract = "This paper presents a study to understand the issues related to using NLG to humanise explanations from a popular interpretable machine learning frameworkcalled LIME. Our study shows that selfreported rating of NLG explanation washigher than that for a non-NLG explanation. However, when tested for comprehension, the results were not as clearcut showing the need for performing more studies to uncover the factors responsible for high-quality NLG explanations.",
author = "James Forrest and Somayajulu Sripada and Wei Pang and George Coghill",
note = "I would like to acknowledge the support given to me by the Engineering and Physical Sciences Research Council (EPSRC) DTP grant number EP/N509814/1.",
year = "2018",
month = "11",
day = "30",
language = "English",
isbn = "9781948087865",
pages = "177--182",
editor = "Emiel Krahmer and Albert Gatt and Martijn Goudbeek",
booktitle = "Proceedings of The 11th International Natural Language Generation Conference",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Towards making NLG a voice for interpretable Machine Learning

AU - Forrest, James

AU - Sripada, Somayajulu

AU - Pang, Wei

AU - Coghill, George

N1 - I would like to acknowledge the support given to me by the Engineering and Physical Sciences Research Council (EPSRC) DTP grant number EP/N509814/1.

PY - 2018/11/30

Y1 - 2018/11/30

N2 - This paper presents a study to understand the issues related to using NLG to humanise explanations from a popular interpretable machine learning frameworkcalled LIME. Our study shows that selfreported rating of NLG explanation washigher than that for a non-NLG explanation. However, when tested for comprehension, the results were not as clearcut showing the need for performing more studies to uncover the factors responsible for high-quality NLG explanations.

AB - This paper presents a study to understand the issues related to using NLG to humanise explanations from a popular interpretable machine learning frameworkcalled LIME. Our study shows that selfreported rating of NLG explanation washigher than that for a non-NLG explanation. However, when tested for comprehension, the results were not as clearcut showing the need for performing more studies to uncover the factors responsible for high-quality NLG explanations.

M3 - Conference contribution

SN - 9781948087865

SP - 177

EP - 182

BT - Proceedings of The 11th International Natural Language Generation Conference

A2 - Krahmer, Emiel

A2 - Gatt, Albert

A2 - Goudbeek, Martijn

PB - Association for Computational Linguistics (ACL)

ER -