Generating English Summaries of Time Series Data Using the Gricean Maxims

Gowri Somayajulu Sripada, Ehud Baruch Reiter, James Ritchie Wallace Hunter, J. Yu

Research output: Chapter in Book/Report/Conference proceedingChapter

30 Citations (Scopus)

Abstract

We are developing technology for generating English textual summaries of time-series data, in three domains: weather forecasts, gas-turbine sensor readings, and hospital intensive care data. Our weather-forecast generator is currently operational and being used daily by a meteorological company. We generate summaries in three steps: (a) selecting the most important trends and patterns to communicate; (b) mapping these patterns onto words and phrases; and (c) generating actual texts based on these words and phrases. In this paper we focus on the first step, (a), selecting the information to communicate, and describe how we perform this using modified versions of standard data analysis algorithms such as segmentation. The modifications arose out of empirical work with users and domain experts, and in fact can all be regarded as applications of the Gricean maxims of Quality, Quantity, Relevance, and Manner, which describe how a cooperative speaker should behave in order to help a hearer correctly interpret a text. The Gricean maxims are perhaps a key element of adapting data analysis algorithms for effective communication of information to human users, and should be considered by other researchers interested in communicating data to human users.
Original languageEnglish
Title of host publicationProceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2003)
PublisherACM Press
Pages187-196
ISBN (Electronic)ISBN:1-58113-737-0
DOIs
Publication statusPublished - Aug 2003

Fingerprint

Time series
Gas turbines
Communication
Sensors
Industry

Cite this

Sripada, G. S., Reiter, E. B., Hunter, J. R. W., & Yu, J. (2003). Generating English Summaries of Time Series Data Using the Gricean Maxims. In Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2003) (pp. 187-196). ACM Press. https://doi.org/10.1145/956750.956774

Generating English Summaries of Time Series Data Using the Gricean Maxims. / Sripada, Gowri Somayajulu; Reiter, Ehud Baruch; Hunter, James Ritchie Wallace; Yu, J.

Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2003). ACM Press, 2003. p. 187-196.

Research output: Chapter in Book/Report/Conference proceedingChapter

Sripada, GS, Reiter, EB, Hunter, JRW & Yu, J 2003, Generating English Summaries of Time Series Data Using the Gricean Maxims. in Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2003). ACM Press, pp. 187-196. https://doi.org/10.1145/956750.956774
Sripada GS, Reiter EB, Hunter JRW, Yu J. Generating English Summaries of Time Series Data Using the Gricean Maxims. In Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2003). ACM Press. 2003. p. 187-196 https://doi.org/10.1145/956750.956774
Sripada, Gowri Somayajulu ; Reiter, Ehud Baruch ; Hunter, James Ritchie Wallace ; Yu, J. / Generating English Summaries of Time Series Data Using the Gricean Maxims. Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2003). ACM Press, 2003. pp. 187-196
@inbook{bb7badb3564b493fad2983da3063e4b0,
title = "Generating English Summaries of Time Series Data Using the Gricean Maxims",
abstract = "We are developing technology for generating English textual summaries of time-series data, in three domains: weather forecasts, gas-turbine sensor readings, and hospital intensive care data. Our weather-forecast generator is currently operational and being used daily by a meteorological company. We generate summaries in three steps: (a) selecting the most important trends and patterns to communicate; (b) mapping these patterns onto words and phrases; and (c) generating actual texts based on these words and phrases. In this paper we focus on the first step, (a), selecting the information to communicate, and describe how we perform this using modified versions of standard data analysis algorithms such as segmentation. The modifications arose out of empirical work with users and domain experts, and in fact can all be regarded as applications of the Gricean maxims of Quality, Quantity, Relevance, and Manner, which describe how a cooperative speaker should behave in order to help a hearer correctly interpret a text. The Gricean maxims are perhaps a key element of adapting data analysis algorithms for effective communication of information to human users, and should be considered by other researchers interested in communicating data to human users.",
author = "Sripada, {Gowri Somayajulu} and Reiter, {Ehud Baruch} and Hunter, {James Ritchie Wallace} and J. Yu",
year = "2003",
month = "8",
doi = "10.1145/956750.956774",
language = "English",
pages = "187--196",
booktitle = "Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2003)",
publisher = "ACM Press",

}

TY - CHAP

T1 - Generating English Summaries of Time Series Data Using the Gricean Maxims

AU - Sripada, Gowri Somayajulu

AU - Reiter, Ehud Baruch

AU - Hunter, James Ritchie Wallace

AU - Yu, J.

PY - 2003/8

Y1 - 2003/8

N2 - We are developing technology for generating English textual summaries of time-series data, in three domains: weather forecasts, gas-turbine sensor readings, and hospital intensive care data. Our weather-forecast generator is currently operational and being used daily by a meteorological company. We generate summaries in three steps: (a) selecting the most important trends and patterns to communicate; (b) mapping these patterns onto words and phrases; and (c) generating actual texts based on these words and phrases. In this paper we focus on the first step, (a), selecting the information to communicate, and describe how we perform this using modified versions of standard data analysis algorithms such as segmentation. The modifications arose out of empirical work with users and domain experts, and in fact can all be regarded as applications of the Gricean maxims of Quality, Quantity, Relevance, and Manner, which describe how a cooperative speaker should behave in order to help a hearer correctly interpret a text. The Gricean maxims are perhaps a key element of adapting data analysis algorithms for effective communication of information to human users, and should be considered by other researchers interested in communicating data to human users.

AB - We are developing technology for generating English textual summaries of time-series data, in three domains: weather forecasts, gas-turbine sensor readings, and hospital intensive care data. Our weather-forecast generator is currently operational and being used daily by a meteorological company. We generate summaries in three steps: (a) selecting the most important trends and patterns to communicate; (b) mapping these patterns onto words and phrases; and (c) generating actual texts based on these words and phrases. In this paper we focus on the first step, (a), selecting the information to communicate, and describe how we perform this using modified versions of standard data analysis algorithms such as segmentation. The modifications arose out of empirical work with users and domain experts, and in fact can all be regarded as applications of the Gricean maxims of Quality, Quantity, Relevance, and Manner, which describe how a cooperative speaker should behave in order to help a hearer correctly interpret a text. The Gricean maxims are perhaps a key element of adapting data analysis algorithms for effective communication of information to human users, and should be considered by other researchers interested in communicating data to human users.

U2 - 10.1145/956750.956774

DO - 10.1145/956750.956774

M3 - Chapter

SP - 187

EP - 196

BT - Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2003)

PB - ACM Press

ER -