DROPS

Document

DOI: 10.4230/OASIcs.SLATE.2016.2

A Re-Ranking Method Based on Irrelevant Documents in Ad-Hoc Retrieval

Authors: Rabeb Mbarek, Mohamed Tmar, Hawete Hattab, and Mohand Boughanem

Published in: OASIcs, Volume 51, 5th Symposium on Languages, Applications and Technologies (SLATE'16) (2016)

Abstract

In this paper, we propose a novel approach for document re-ranking, which relies on the concept of negative feedback represented by irrelevant documents. In a previous paper, a pseudo-relevance feedback method is introduced using an absorbing document ~d which best fits the user's need. The document ~d is orthogonal to the majority of irrelevant documents. In this paper, this document is used to re-rank the initial set of ranked documents in Ad-hoc retrieval. The evaluation carried out on a standard document collection shows the effectiveness of the proposed approach.

Cite as

Rabeb Mbarek, Mohamed Tmar, Hawete Hattab, and Mohand Boughanem. A Re-Ranking Method Based on Irrelevant Documents in Ad-Hoc Retrieval. In 5th Symposium on Languages, Applications and Technologies (SLATE'16). Open Access Series in Informatics (OASIcs), Volume 51, pp. 2:1-2:10, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2016)

Copy BibTex To Clipboard

@InProceedings{mbarek_et_al:OASIcs.SLATE.2016.2,
  author =	{Mbarek, Rabeb and Tmar, Mohamed and Hattab, Hawete and Boughanem, Mohand},
  title =	{{A Re-Ranking Method Based on Irrelevant Documents in Ad-Hoc Retrieval}},
  booktitle =	{5th Symposium on Languages, Applications and Technologies (SLATE'16)},
  pages =	{2:1--2:10},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-006-4},
  ISSN =	{2190-6807},
  year =	{2016},
  volume =	{51},
  editor =	{Mernik, Marjan and Leal, Jos\'{e} Paulo and Gon\c{c}alo Oliveira, Hugo},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.SLATE.2016.2},
  URN =		{urn:nbn:de:0030-drops-60072},
  doi =		{10.4230/OASIcs.SLATE.2016.2},
  annote =	{Keywords: Re-ranking, absorption of irrelevance, vector product}
}

Document

DOI: 10.4230/OASIcs.SLATE.2014.215

Rocchio's Model Based on Vector Space Basis Change for Pseudo Relevance Feedback

Authors: Rabeb Mbarek, Mohamed Tmar, and Hawete Hattab

Published in: OASIcs, Volume 38, 3rd Symposium on Languages, Applications and Technologies (2014)

Abstract

Rocchio's relevance feedback model is a classic query expansion method and it has been shown to be effective in boosting information retrieval performance. The main problem with this method is that the relevant and the irrelevant documents overlap in the vector space because they often share same terms (at least the terms of the query). With respect to the initial vector space basis (index terms), it is difficult to select terms that separate relevant and irrelevant documents. The Vector Space Basis Change is used to separate relevant and irrelevant documents without any modification on the query term weights. In this paper, first, we study how to incorporate Vector Space Basis Change into the Rocchio's model. Second, we propose Rocchio's models based on Vector Space Basis Change, called VSBCRoc models. Experimental results on a TREC collection show that our proposed models are effective.

Cite as

Rabeb Mbarek, Mohamed Tmar, and Hawete Hattab. Rocchio's Model Based on Vector Space Basis Change for Pseudo Relevance Feedback. In 3rd Symposium on Languages, Applications and Technologies. Open Access Series in Informatics (OASIcs), Volume 38, pp. 215-224, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2014)

Copy BibTex To Clipboard

@InProceedings{mbarek_et_al:OASIcs.SLATE.2014.215,
  author =	{Mbarek, Rabeb and Tmar, Mohamed and Hattab, Hawete},
  title =	{{Rocchio's Model Based on Vector Space Basis Change for Pseudo Relevance Feedback}},
  booktitle =	{3rd Symposium on Languages, Applications and Technologies},
  pages =	{215--224},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-939897-68-2},
  ISSN =	{2190-6807},
  year =	{2014},
  volume =	{38},
  editor =	{Pereira, Maria Jo\~{a}o Varanda and Leal, Jos\'{e} Paulo and Sim\~{o}es, Alberto},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.SLATE.2014.215},
  URN =		{urn:nbn:de:0030-drops-45713},
  doi =		{10.4230/OASIcs.SLATE.2014.215},
  annote =	{Keywords: Rocchio model, vector space basis change, pseudo relevance feedback}
}

Search Results

Documents authored by Tmar, Mohamed

A Re-Ranking Method Based on Irrelevant Documents in Ad-Hoc Retrieval

Abstract

Cite as

Rocchio's Model Based on Vector Space Basis Change for Pseudo Relevance Feedback

Abstract

Cite as

Thanks for your feedback!

Could not send message