A new probabilistic ranking model

Richard Connor, Robert Moss, Morgan Harvey

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

1 Citation (Scopus)

Abstract

Over the years a number of models have been introduced as solutions to the central IR problem of ranking documents given textual queries. Here we define another new model. It is a probabilistic model and has no term inter-dependencies, thus allowing calculation from inverted indices. It is based upon a simple core hypothesis, directly calculating a ranking score in terms of probability theory. Early results show that its performance is credible, even in the absence of parameters or heuristics. Its semantic basis gives absolute results, allowing different rankings to be compared with each other. The investigation of this model is at a very early stage; here, we simply propose the model for further investigation.
LanguageEnglish
Title of host publicationProceeding ICTIR '13 Proceedings of the 2013 Conference on the Theory of Information Retrieval
EditorsOrlen Kurland, Donald Metzler, Christina Lioma, Birger Larsen, Peter Ingwersen
Place of PublicationNew York, NY
Pages109-112
Number of pages4
DOIs
Publication statusPublished - 29 Sep 2013
Event2013 Conference on the Theory of Information Retrieval - Copenhagen, Denmark
Duration: 29 Sep 20132 Oct 2013

Conference

Conference2013 Conference on the Theory of Information Retrieval
CountryDenmark
CityCopenhagen
Period29/09/132/10/13

Fingerprint

Semantics
Statistical Models

Keywords

  • information retrieval
  • ranking documents
  • probabilistic retrieval
  • Jensen-Shannon divergence
  • textual queries

Cite this

Connor, R., Moss, R., & Harvey, M. (2013). A new probabilistic ranking model. In O. Kurland, D. Metzler, C. Lioma, B. Larsen, & P. Ingwersen (Eds.), Proceeding ICTIR '13 Proceedings of the 2013 Conference on the Theory of Information Retrieval (pp. 109-112). [23] New York, NY. https://doi.org/10.1145/2499178.2499185
Connor, Richard ; Moss, Robert ; Harvey, Morgan. / A new probabilistic ranking model. Proceeding ICTIR '13 Proceedings of the 2013 Conference on the Theory of Information Retrieval. editor / Orlen Kurland ; Donald Metzler ; Christina Lioma ; Birger Larsen ; Peter Ingwersen. New York, NY, 2013. pp. 109-112
@inproceedings{bc7327bbaf5f4b36aedd5069868a7036,
title = "A new probabilistic ranking model",
abstract = "Over the years a number of models have been introduced as solutions to the central IR problem of ranking documents given textual queries. Here we define another new model. It is a probabilistic model and has no term inter-dependencies, thus allowing calculation from inverted indices. It is based upon a simple core hypothesis, directly calculating a ranking score in terms of probability theory. Early results show that its performance is credible, even in the absence of parameters or heuristics. Its semantic basis gives absolute results, allowing different rankings to be compared with each other. The investigation of this model is at a very early stage; here, we simply propose the model for further investigation.",
keywords = "information retrieval, ranking documents, probabilistic retrieval, Jensen-Shannon divergence, textual queries",
author = "Richard Connor and Robert Moss and Morgan Harvey",
year = "2013",
month = "9",
day = "29",
doi = "10.1145/2499178.2499185",
language = "English",
isbn = "9781450321075",
pages = "109--112",
editor = "Orlen Kurland and Donald Metzler and Christina Lioma and Birger Larsen and Peter Ingwersen",
booktitle = "Proceeding ICTIR '13 Proceedings of the 2013 Conference on the Theory of Information Retrieval",

}

Connor, R, Moss, R & Harvey, M 2013, A new probabilistic ranking model. in O Kurland, D Metzler, C Lioma, B Larsen & P Ingwersen (eds), Proceeding ICTIR '13 Proceedings of the 2013 Conference on the Theory of Information Retrieval., 23, New York, NY, pp. 109-112, 2013 Conference on the Theory of Information Retrieval, Copenhagen, Denmark, 29/09/13. https://doi.org/10.1145/2499178.2499185

A new probabilistic ranking model. / Connor, Richard; Moss, Robert ; Harvey, Morgan.

Proceeding ICTIR '13 Proceedings of the 2013 Conference on the Theory of Information Retrieval. ed. / Orlen Kurland; Donald Metzler; Christina Lioma; Birger Larsen; Peter Ingwersen. New York, NY, 2013. p. 109-112 23.

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

TY - GEN

T1 - A new probabilistic ranking model

AU - Connor, Richard

AU - Moss, Robert

AU - Harvey, Morgan

PY - 2013/9/29

Y1 - 2013/9/29

N2 - Over the years a number of models have been introduced as solutions to the central IR problem of ranking documents given textual queries. Here we define another new model. It is a probabilistic model and has no term inter-dependencies, thus allowing calculation from inverted indices. It is based upon a simple core hypothesis, directly calculating a ranking score in terms of probability theory. Early results show that its performance is credible, even in the absence of parameters or heuristics. Its semantic basis gives absolute results, allowing different rankings to be compared with each other. The investigation of this model is at a very early stage; here, we simply propose the model for further investigation.

AB - Over the years a number of models have been introduced as solutions to the central IR problem of ranking documents given textual queries. Here we define another new model. It is a probabilistic model and has no term inter-dependencies, thus allowing calculation from inverted indices. It is based upon a simple core hypothesis, directly calculating a ranking score in terms of probability theory. Early results show that its performance is credible, even in the absence of parameters or heuristics. Its semantic basis gives absolute results, allowing different rankings to be compared with each other. The investigation of this model is at a very early stage; here, we simply propose the model for further investigation.

KW - information retrieval

KW - ranking documents

KW - probabilistic retrieval

KW - Jensen-Shannon divergence

KW - textual queries

U2 - 10.1145/2499178.2499185

DO - 10.1145/2499178.2499185

M3 - Conference contribution book

SN - 9781450321075

SP - 109

EP - 112

BT - Proceeding ICTIR '13 Proceedings of the 2013 Conference on the Theory of Information Retrieval

A2 - Kurland, Orlen

A2 - Metzler, Donald

A2 - Lioma, Christina

A2 - Larsen, Birger

A2 - Ingwersen, Peter

CY - New York, NY

ER -

Connor R, Moss R, Harvey M. A new probabilistic ranking model. In Kurland O, Metzler D, Lioma C, Larsen B, Ingwersen P, editors, Proceeding ICTIR '13 Proceedings of the 2013 Conference on the Theory of Information Retrieval. New York, NY. 2013. p. 109-112. 23 https://doi.org/10.1145/2499178.2499185