Integrating quality of information with pragmatic assistance

James Edwards, Taylor Cassidy, Geeth De Mel, Thomas F. La Porta

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

1 Citation (Scopus)

Abstract

In this work, we propose a framework for resolving ambiguity in user-generated natural language queries. We use pragmatics to formalize the refinement of an incoming query into possible interpretations which we call a response graph. Each of the possible interpretations are assigned likelihoods of being correct by the pragmatics framework, as well as Quality of Information (QoI) scores that quantify how useful we expect the response to be. We discuss two schemes for traversing the response graph and determining the querent's intended meaning, an up-front one-shot algorithm ("static") and an iterative runtime algorithm ("dynamic"). We analyze the performance of these two schemes by presenting data from simulated conversations between a querent and system using randomly generated response graphs. We show that both schemes are able to achieve a significant reduction in the cost to retrieve the desired information, allowing such a system to make more intelligent decisions about how to handle and respond to natural language queries.

Original languageEnglish (US)
Title of host publication2016 IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509019410
DOIs
StatePublished - Apr 19 2016
Event13th IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016 - Sydney, Australia
Duration: Mar 14 2016Mar 18 2016

Publication series

Name2016 IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016

Other

Other13th IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016
CountryAustralia
CitySydney
Period3/14/163/18/16

Fingerprint

Query languages
Costs

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computer Networks and Communications
  • Human-Computer Interaction

Cite this

Edwards, J., Cassidy, T., De Mel, G., & La Porta, T. F. (2016). Integrating quality of information with pragmatic assistance. In 2016 IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016 [7457127] (2016 IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PERCOMW.2016.7457127
Edwards, James ; Cassidy, Taylor ; De Mel, Geeth ; La Porta, Thomas F. / Integrating quality of information with pragmatic assistance. 2016 IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016. Institute of Electrical and Electronics Engineers Inc., 2016. (2016 IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016).
@inproceedings{25f2a2f7007945c38a983315ca90df10,
title = "Integrating quality of information with pragmatic assistance",
abstract = "In this work, we propose a framework for resolving ambiguity in user-generated natural language queries. We use pragmatics to formalize the refinement of an incoming query into possible interpretations which we call a response graph. Each of the possible interpretations are assigned likelihoods of being correct by the pragmatics framework, as well as Quality of Information (QoI) scores that quantify how useful we expect the response to be. We discuss two schemes for traversing the response graph and determining the querent's intended meaning, an up-front one-shot algorithm ({"}static{"}) and an iterative runtime algorithm ({"}dynamic{"}). We analyze the performance of these two schemes by presenting data from simulated conversations between a querent and system using randomly generated response graphs. We show that both schemes are able to achieve a significant reduction in the cost to retrieve the desired information, allowing such a system to make more intelligent decisions about how to handle and respond to natural language queries.",
author = "James Edwards and Taylor Cassidy and {De Mel}, Geeth and {La Porta}, {Thomas F.}",
year = "2016",
month = "4",
day = "19",
doi = "10.1109/PERCOMW.2016.7457127",
language = "English (US)",
series = "2016 IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2016 IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016",
address = "United States",

}

Edwards, J, Cassidy, T, De Mel, G & La Porta, TF 2016, Integrating quality of information with pragmatic assistance. in 2016 IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016., 7457127, 2016 IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016, Institute of Electrical and Electronics Engineers Inc., 13th IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016, Sydney, Australia, 3/14/16. https://doi.org/10.1109/PERCOMW.2016.7457127

Integrating quality of information with pragmatic assistance. / Edwards, James; Cassidy, Taylor; De Mel, Geeth; La Porta, Thomas F.

2016 IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016. Institute of Electrical and Electronics Engineers Inc., 2016. 7457127 (2016 IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016).

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

TY - GEN

T1 - Integrating quality of information with pragmatic assistance

AU - Edwards, James

AU - Cassidy, Taylor

AU - De Mel, Geeth

AU - La Porta, Thomas F.

PY - 2016/4/19

Y1 - 2016/4/19

N2 - In this work, we propose a framework for resolving ambiguity in user-generated natural language queries. We use pragmatics to formalize the refinement of an incoming query into possible interpretations which we call a response graph. Each of the possible interpretations are assigned likelihoods of being correct by the pragmatics framework, as well as Quality of Information (QoI) scores that quantify how useful we expect the response to be. We discuss two schemes for traversing the response graph and determining the querent's intended meaning, an up-front one-shot algorithm ("static") and an iterative runtime algorithm ("dynamic"). We analyze the performance of these two schemes by presenting data from simulated conversations between a querent and system using randomly generated response graphs. We show that both schemes are able to achieve a significant reduction in the cost to retrieve the desired information, allowing such a system to make more intelligent decisions about how to handle and respond to natural language queries.

AB - In this work, we propose a framework for resolving ambiguity in user-generated natural language queries. We use pragmatics to formalize the refinement of an incoming query into possible interpretations which we call a response graph. Each of the possible interpretations are assigned likelihoods of being correct by the pragmatics framework, as well as Quality of Information (QoI) scores that quantify how useful we expect the response to be. We discuss two schemes for traversing the response graph and determining the querent's intended meaning, an up-front one-shot algorithm ("static") and an iterative runtime algorithm ("dynamic"). We analyze the performance of these two schemes by presenting data from simulated conversations between a querent and system using randomly generated response graphs. We show that both schemes are able to achieve a significant reduction in the cost to retrieve the desired information, allowing such a system to make more intelligent decisions about how to handle and respond to natural language queries.

UR - http://www.scopus.com/inward/record.url?scp=84966679933&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84966679933&partnerID=8YFLogxK

U2 - 10.1109/PERCOMW.2016.7457127

DO - 10.1109/PERCOMW.2016.7457127

M3 - Conference contribution

AN - SCOPUS:84966679933

T3 - 2016 IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016

BT - 2016 IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Edwards J, Cassidy T, De Mel G, La Porta TF. Integrating quality of information with pragmatic assistance. In 2016 IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016. Institute of Electrical and Electronics Engineers Inc. 2016. 7457127. (2016 IEEE International Conference on Pervasive Computing and Communication Workshops, PerCom Workshops 2016). https://doi.org/10.1109/PERCOMW.2016.7457127