Conceptual Language Models for Context-Aware Text Retrieval

Abstract

While participating in the HARD track our first question was, what an IR-application should look like that takes into account preference meta-data from the user, without the need of explicit (manual) meta-data tagging of the collection. Especially, we touch the question how contextual information can be described in an abstract model appropriate for the IR-task, which further allows improving and fine-tuning of the context representations by learning from the user. As a first result, we roughly sketch a system architecture and context representation based on statistical language models that fits well to the task of the HARD track. Furthermore, we discuss issues of ranking and score normalizations on this background.
Original languageUndefined
Title of host publicationProceedings of the 13th Text REtrieval Conference Proceedings (TREC)
EditorsE.M Voorhees, Lori P. Buckland
Place of PublicationGaithersburg, Maryland, USA
PublisherNational Institute of Standards and Technology (NIST)
Pages99
Number of pages8
ISBN (Print)not assigned
StatePublished - May 2005
EventThirteenth Text REtrieval Conference, TREC-13 2004 - Gaithersburg, United States

Publication series

NameNIST Special Publications
PublisherNational Institute of Standards and Technology (NIST)
VolumeSP 500-261

Conference

ConferenceThirteenth Text REtrieval Conference, TREC-13 2004
Abbreviated titleTREC
CountryUnited States
CityGaithersburg
Period16/11/0419/11/04

Fingerprint

user
normalization
fine
architecture
preference
score
learning
system
data

Keywords

  • EWI-7326
  • IR-63532
  • METIS-225950
  • DB-XMLIR: XML INFORMATION RETRIEVAL

Cite this

Rode, H., & Hiemstra, D. (2005). Conceptual Language Models for Context-Aware Text Retrieval. In E. M. Voorhees, & L. P. Buckland (Eds.), Proceedings of the 13th Text REtrieval Conference Proceedings (TREC) (pp. 99). (NIST Special Publications; Vol. SP 500-261). Gaithersburg, Maryland, USA: National Institute of Standards and Technology (NIST).

Rode, H.; Hiemstra, Djoerd / Conceptual Language Models for Context-Aware Text Retrieval.

Proceedings of the 13th Text REtrieval Conference Proceedings (TREC). ed. / E.M Voorhees; Lori P. Buckland. Gaithersburg, Maryland, USA : National Institute of Standards and Technology (NIST), 2005. p. 99 (NIST Special Publications; Vol. SP 500-261).

Research output: Scientific - peer-reviewConference contribution

@inbook{97c1e906111c46248ea39002b6d3d351,
title = "Conceptual Language Models for Context-Aware Text Retrieval",
abstract = "While participating in the HARD track our first question was, what an IR-application should look like that takes into account preference meta-data from the user, without the need of explicit (manual) meta-data tagging of the collection. Especially, we touch the question how contextual information can be described in an abstract model appropriate for the IR-task, which further allows improving and fine-tuning of the context representations by learning from the user. As a first result, we roughly sketch a system architecture and context representation based on statistical language models that fits well to the task of the HARD track. Furthermore, we discuss issues of ranking and score normalizations on this background.",
keywords = "EWI-7326, IR-63532, METIS-225950, DB-XMLIR: XML INFORMATION RETRIEVAL",
author = "H. Rode and Djoerd Hiemstra",
note = "Imported from EWI/DB PMS [db-utwente:inpr:0000003641]",
year = "2005",
month = "5",
isbn = "not assigned",
series = "NIST Special Publications",
publisher = "National Institute of Standards and Technology (NIST)",
pages = "99",
editor = "E.M Voorhees and Buckland, {Lori P.}",
booktitle = "Proceedings of the 13th Text REtrieval Conference Proceedings (TREC)",

}

Rode, H & Hiemstra, D 2005, Conceptual Language Models for Context-Aware Text Retrieval. in EM Voorhees & LP Buckland (eds), Proceedings of the 13th Text REtrieval Conference Proceedings (TREC). NIST Special Publications, vol. SP 500-261, National Institute of Standards and Technology (NIST), Gaithersburg, Maryland, USA, pp. 99, Thirteenth Text REtrieval Conference, TREC-13 2004, Gaithersburg, United States, 16-19 November.

Conceptual Language Models for Context-Aware Text Retrieval. / Rode, H.; Hiemstra, Djoerd.

Proceedings of the 13th Text REtrieval Conference Proceedings (TREC). ed. / E.M Voorhees; Lori P. Buckland. Gaithersburg, Maryland, USA : National Institute of Standards and Technology (NIST), 2005. p. 99 (NIST Special Publications; Vol. SP 500-261).

Research output: Scientific - peer-reviewConference contribution

TY - CHAP

T1 - Conceptual Language Models for Context-Aware Text Retrieval

AU - Rode,H.

AU - Hiemstra,Djoerd

N1 - Imported from EWI/DB PMS [db-utwente:inpr:0000003641]

PY - 2005/5

Y1 - 2005/5

N2 - While participating in the HARD track our first question was, what an IR-application should look like that takes into account preference meta-data from the user, without the need of explicit (manual) meta-data tagging of the collection. Especially, we touch the question how contextual information can be described in an abstract model appropriate for the IR-task, which further allows improving and fine-tuning of the context representations by learning from the user. As a first result, we roughly sketch a system architecture and context representation based on statistical language models that fits well to the task of the HARD track. Furthermore, we discuss issues of ranking and score normalizations on this background.

AB - While participating in the HARD track our first question was, what an IR-application should look like that takes into account preference meta-data from the user, without the need of explicit (manual) meta-data tagging of the collection. Especially, we touch the question how contextual information can be described in an abstract model appropriate for the IR-task, which further allows improving and fine-tuning of the context representations by learning from the user. As a first result, we roughly sketch a system architecture and context representation based on statistical language models that fits well to the task of the HARD track. Furthermore, we discuss issues of ranking and score normalizations on this background.

KW - EWI-7326

KW - IR-63532

KW - METIS-225950

KW - DB-XMLIR: XML INFORMATION RETRIEVAL

M3 - Conference contribution

SN - not assigned

T3 - NIST Special Publications

SP - 99

BT - Proceedings of the 13th Text REtrieval Conference Proceedings (TREC)

PB - National Institute of Standards and Technology (NIST)

ER -

Rode H, Hiemstra D. Conceptual Language Models for Context-Aware Text Retrieval. In Voorhees EM, Buckland LP, editors, Proceedings of the 13th Text REtrieval Conference Proceedings (TREC). Gaithersburg, Maryland, USA: National Institute of Standards and Technology (NIST). 2005. p. 99. (NIST Special Publications).