nach oben

Erschienen in:

2025 | OriginalPaper | Buchkapitel

PR-Rank: A Parameter Regression Approach for Learning-to-Rank Model Adaptation Without Target Domain Data

verfasst von : Takumi Ito, Atsuki Maruta, Makoto P. Kato, Sumio Fujita

Erschienen in: Web Information Systems Engineering – WISE 2024

Verlag: Springer Nature Singapore

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

This paper addresses a problem of constructing a Learning-to-Rank (LtR) model tailored to a target domain without using any domain-specific queries and relevance judgements. Our proposed method, PR-Rank, incorporates domain features, which are represented in a real-valued vector and can be estimated by domain experts, for adapting LtR models. The key component in our method is a parameter regression model that learns to regress the optimal parameters of the LtR model from the domain features. This eliminates the need for access to users’ queries and relevance judgements in a target domain, which is often unavailable in new and emerging services. In our experiments, we compared the performance of the proposed method against a domain-agnostic method, using publicly available LtR datasets including OHSUMED, MQ2007/2008, TREC Web track, and MSLR. The results showed that our method could outperform the baseline model trained on a large amount of data without considering domain differences.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Nächstes Kapitel Weighted Linear Regression with Optimized Gap for Learned Index

The code is available at https://github.com/kasys-lab/PR-Rank.

https://fasttext.cc/docs/en/language-identification.html.

http://www.odp.org/.

https://www.kaggle.com/datasets/lucmichalski/dmoz-bert-multiclass-web-classification-dataset/.

https://sourceforge.net/p/lemur/wiki/RankLib/.

The difference between the PR-Rank and ideal models was not tested since we did not expect that PR-Rank outperform the ideal model.

Bennett, P.N., Svore, K., Dumais, S.T.: Classification-enhanced ranking. In: WWW, pp. 111–120 (2010)

Chen, D., Xiong, Y., Yan, J., Xue, G.R., Wang, G., Chen, Z.: Knowledge transfer for cross domain learning to rank. Inf. Retrieval 13(3), 236–253 (2010)

Dato, D., MacAvaney, S., Nardini, F.M., Perego, R., Tonellotto, N.: The istella22 dataset: Bridging traditional and neural learning to rank evaluation. In: SIGIR, pp. 3099–3107 (2022)

Gao, J., et al.: Model adaptation via model interpolation and boosting for web search ranking. In: EMNLP, pp. 505–513 (2009)

Gao, W., Cai, P., Wong, K.F., Zhou, A.: Learning to rank only using training data from related domain. In: SIGIR, pp. 162–169 (2010)

Geng, X., Liu, T.Y., Qin, T., Arnold, A., Li, H., Shum, H.Y.: Query dependent ranking using k-nearest neighbor. In: SIGIR, pp. 115–122 (2008)

Ghanbari, E., Shakery, A.: Query-dependent learning to rank for cross-lingual information retrieval. Knowl. Inf. Syst. 59(3), 711–743 (2019)CrossRef

Goswami, P., Amini, M.R., Gaussier, E.: Transferring knowledge with source selection to learn IR functions on unlabeled collections. In: CIKM, pp. 2315–2320 (2013)

Guo, Q., Chen, W., Wan, H.: AOL4PS: a large-scale data set for personalized search. Data Intell. 3(4), 548–567 (2021)CrossRef

10.

Hashemi, H., Zhuang, Y., Kothur, S.S.R., Prasad, S., Meij, E., Bruce Croft, W.: Dense retrieval adaptation using target domain description. In: ICTIR, pp. 95–104 (2023)

11.

Liu, T.Y., et al.: Learning to rank for information retrieval. Found. Trends® Inf. Retrieval 3(3), 225–331 (2009)

12.

Long, B., Lamkhede, S., Vadrevu, S., Zhang, Y., Tseng, B.: A risk minimization framework for domain adaptation. In: CIKM, pp. 1347–1356 (2009)

13.

Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11), 2579–2605 (2008)

14.

MacAvaney, S., Macdonald, C., Ounis, I.: Reproducing personalised session search over the AOL query log. In: ECIR, pp. 627–640 (2022)

15.

Macdonald, C., Dinçer, B.T., Ounis, I.: Transferring learning to rank models for web search. In: ICTIR, pp. 41–50 (2015)

16.

MacQueen, J., et al.: Some methods for classification and analysis of multivariate observations. In: Proceedings of the fifth Berkeley Symposium on Mathematical Statistics and Probability, vol. 1, pp. 281–297 (1967)

17.

Ni, W., Huang, Y., Xie, M.: A query dependent approach to learning to rank for information retrieval. In: WAIM, pp. 262–269 (2008)

18.

Peng, J., Macdonald, C., Ounis, I.: Learning to select a ranking function. In: ECIR, pp. 114–126 (2010)

19.

Qin, T., Liu, T.Y.: Introducing LETOR 4.0 datasets (2013). http://arxiv.org/abs/1306.2597

20.

Qin, T., Liu, T.Y., Xu, J., Li, H.: LETOR: a benchmark collection for research on learning to rank for information retrieval. Inf. Retrieval 13(4), 346–374 (2010)CrossRef

21.

Robertson, S., Zaragoza, H.: The probabilistic relevance framework: BM25 and beyond. Found. Trends®Inf. Retrieval 3(4), 333–389 (2009)

22.

Senter, R., Smith, E.A.: Automated readability index. AMRL-TR. Aerospace Medical Research Laboratories, pp. 1–11 (1967)

23.

Sun, S., et al.: Few-Shot text ranking with meta adapted synthetic weak supervision. In: ACL, pp. 5030–5043 (2020)

24.

Wang, K., Thakur, N., Reimers, N., Gurevych, I.: GPL: generative pseudo labeling for unsupervised domain adaptation of dense retrieval. In: NAACL, pp. 2345–2360 (2022)

25.

Zhu, P., Hauff, C.: Unsupervised domain adaptation for question generation with domain data selection and self-training. In: NAACL, pp. 2388–2401 (2022)

Titel: PR-Rank: A Parameter Regression Approach for Learning-to-Rank Model Adaptation Without Target Domain Data
verfasst von: Takumi Ito
Atsuki Maruta
Makoto P. Kato
Sumio Fujita
Verlag: Springer Nature Singapore
Buch: Web Information Systems Engineering – WISE 2024
Print ISBN: 978-981-9605-72-9

Electronic ISBN: 978-981-9605-73-6

Copyright-Jahr: 2025
DOI: https://doi.org/10.1007/978-981-96-0573-6_1

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"