Competitive Retrieval: Going Beyond the Single Query

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Nachimovsky, Haya, Tennenholtz, Moshe, Raiber, Fiana, Kurland, Oren
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911839142543360
author Nachimovsky, Haya
Tennenholtz, Moshe
Raiber, Fiana
Kurland, Oren
author_facet Nachimovsky, Haya
Tennenholtz, Moshe
Raiber, Fiana
Kurland, Oren
contents Previous work on the competitive retrieval setting focused on a single-query setting: document authors manipulate their documents so as to improve their future ranking for a given query. We study a competitive setting where authors opt to improve their document's ranking for multiple queries. We use game theoretic analysis to prove that equilibrium does not necessarily exist. We then empirically show that it is more difficult for authors to improve their documents' rankings for multiple queries with a neural ranker than with a state-of-the-art feature-based ranker. We also present an effective approach for predicting the document most highly ranked in the next induced ranking.
format Preprint
id arxiv_https___arxiv_org_abs_2404_09253
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Competitive Retrieval: Going Beyond the Single Query
Nachimovsky, Haya
Tennenholtz, Moshe
Raiber, Fiana
Kurland, Oren
Information Retrieval
Computer Science and Game Theory
Previous work on the competitive retrieval setting focused on a single-query setting: document authors manipulate their documents so as to improve their future ranking for a given query. We study a competitive setting where authors opt to improve their document's ranking for multiple queries. We use game theoretic analysis to prove that equilibrium does not necessarily exist. We then empirically show that it is more difficult for authors to improve their documents' rankings for multiple queries with a neural ranker than with a state-of-the-art feature-based ranker. We also present an effective approach for predicting the document most highly ranked in the next induced ranking.
title Competitive Retrieval: Going Beyond the Single Query
topic Information Retrieval
Computer Science and Game Theory
url https://arxiv.org/abs/2404.09253