Learning to rank (LtR) techniques leverage assessed samples of query-document relevance to learn effective ranking functions able to exploit the noisy signals hidden in the features used to represent queries and documents. In this paper we explore how to enhance the state-of-the-art LambdaMart LtR algorithm by integrating in the training process an explicit knowledge of the underlying user-interaction model and the possibility of targeting different objective functions that can effectively drive the algorithm towards promising areas of the search space. We enrich the iterative process followed by the learning algorithm in two ways: (1) by considering complex query-based user dynamics instead than simply discounting the gain by the rank position; (2) by designing a learning path across different loss functions that can capture different signals in the training data. Our extensive experiments, conducted on publicly available datasets, show that the proposed solution permits to improve various ranking quality measures by statistically significant margins.

Boosting learning to rank with user dynamics and continuation methods

Lucchese C.;
2019

Abstract

Learning to rank (LtR) techniques leverage assessed samples of query-document relevance to learn effective ranking functions able to exploit the noisy signals hidden in the features used to represent queries and documents. In this paper we explore how to enhance the state-of-the-art LambdaMart LtR algorithm by integrating in the training process an explicit knowledge of the underlying user-interaction model and the possibility of targeting different objective functions that can effectively drive the algorithm towards promising areas of the search space. We enrich the iterative process followed by the learning algorithm in two ways: (1) by considering complex query-based user dynamics instead than simply discounting the gain by the rank position; (2) by designing a learning path across different loss functions that can capture different signals in the training data. Our extensive experiments, conducted on publicly available datasets, show that the proposed solution permits to improve various ranking quality measures by statistically significant margins.
File in questo prodotto:
File Dimensione Formato  
Ferro2019_Article_BoostingLearningToRankWithUser.pdf

non disponibili

Tipologia: Versione dell'editore
Licenza: Accesso chiuso-personale
Dimensione 1.59 MB
Formato Adobe PDF
1.59 MB Adobe PDF   Visualizza/Apri
special_issue_IRJ_2019.pdf

accesso aperto

Tipologia: Documento in Post-print
Licenza: Accesso gratuito (solo visione)
Dimensione 683.83 kB
Formato Adobe PDF
683.83 kB Adobe PDF Visualizza/Apri

I documenti in ARCA sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/10278/3724417
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 5
social impact