Towards making NLG a voice for interpretable Machine Learning

James Forrest; Somayajulu Sripada; Wei Pang; George Coghill

Towards making NLG a voice for interpretable Machine Learning

James Forrest, Somayajulu Sripada, Wei Pang, George Coghill

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

13 Citations (Scopus)

12 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 language	English
Title of host publication	Proceedings of The 11th International Natural Language Generation Conference
Editors	Emiel Krahmer, Albert Gatt, Martijn Goudbeek
Publisher	Association for Computational Linguistics (ACL)
Pages	177-182
Number of pages	6
ISBN (Print)	9781948087865
Publication status	Published - 30 Nov 2018
Event	11th International Conference on Natural Language Generation (INLG 2018) - Tilburg University, Tilburg, Netherlands Duration: 5 Nov 2018 → 8 Nov 2018

Conference

Conference	11th International Conference on Natural Language Generation (INLG 2018)
Country/Territory	Netherlands
City	Tilburg
Period	5/11/18 → 8/11/18

Bibliographical 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.

Access to Document

Towards making NLG a voice for interpretable Machine Learning
ACL materials are Copyright © 1963-2018 ACL; other materials are copyrighted by their respective copyright holders. Materials prior to 2016 here are licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 International License. Permission is granted to make copies for the purposes of teaching and research. Materials published in or after 2016 are licensed on a Creative Commons Attribution 4.0 License. https://creativecommons.org/licenses/by/4.0/
Final published version, 166 KBLicence: CC BY

https://aclanthology.coli.uni-saarland.de/volumes/proceedings-of-the-11th-international-conference-on-natural-language-generationLicence: CC BY

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). Article W18-6522 Association for Computational Linguistics (ACL). https://aclanthology.coli.uni-saarland.de/volumes/proceedings-of-the-11th-international-conference-on-natural-language-generation

Towards making NLG a voice for interpretable Machine Learning. / Forrest, James; Sripada, Somayajulu; Pang, Wei et al.
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 proceeding › Published conference 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. <https://aclanthology.coli.uni-saarland.de/volumes/proceedings-of-the-11th-international-conference-on-natural-language-generation>

@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.; 11th International Conference on Natural Language Generation (INLG 2018) ; Conference date: 05-11-2018 Through 08-11-2018",

year = "2018",

month = nov,

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 - Published 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)

T2 - 11th International Conference on Natural Language Generation (INLG 2018)

Y2 - 5 November 2018 through 8 November 2018

ER -

Towards making NLG a voice for interpretable Machine Learning

Abstract

Conference

Bibliographical note

Access to Document

Fingerprint

Cite this