beeFormer: Bridging the Gap Between Semantic and Interaction Similarity in Recommender Systems

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F24%3A10492912" target="_blank" >RIV/00216208:11320/24:10492912 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21240/24:00377673

Výsledek na webu

<a href="https://doi.org/10.1145/3640457.3691707" target="_blank" >https://doi.org/10.1145/3640457.3691707</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3640457.3691707" target="_blank" >10.1145/3640457.3691707</a>

Jazyk výsledku

angličtina

Název v původním jazyce

beeFormer: Bridging the Gap Between Semantic and Interaction Similarity in Recommender Systems

Popis výsledku v původním jazyce

Recommender systems often use text-side information to improve their predictions, especially in cold-start or zero-shot recommendation scenarios, where traditional collaborative filtering approaches cannot be used. Many approaches to text-mining side information for recommender systems have been proposed over recent years, with sentence Transformers being the most prominent one. However, these models are trained to predict semantic similarity without utilizing interaction data with hidden patterns specific to recommender systems. In this paper, we propose beeFormer, a framework for training sentence Transformer models with interaction data. We demonstrate that our models trained with beeFormer can transfer knowledge between datasets while outperforming not only semantic similarity sentence Transformers but also traditional collaborative filtering methods. We also show that training on multiple datasets from different domains accumulates knowledge in a single model, unlocking the possibility of trainin

Název v anglickém jazyce

beeFormer: Bridging the Gap Between Semantic and Interaction Similarity in Recommender Systems

Popis výsledku anglicky

Recommender systems often use text-side information to improve their predictions, especially in cold-start or zero-shot recommendation scenarios, where traditional collaborative filtering approaches cannot be used. Many approaches to text-mining side information for recommender systems have been proposed over recent years, with sentence Transformers being the most prominent one. However, these models are trained to predict semantic similarity without utilizing interaction data with hidden patterns specific to recommender systems. In this paper, we propose beeFormer, a framework for training sentence Transformer models with interaction data. We demonstrate that our models trained with beeFormer can transfer knowledge between datasets while outperforming not only semantic similarity sentence Transformers but also traditional collaborative filtering methods. We also show that training on multiple datasets from different domains accumulates knowledge in a single model, unlocking the possibility of trainin

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GX20-16819X" target="_blank" >GX20-16819X: Porozumění jazyku: od syntaxe k diskurzu</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 18th ACM Conference on Recommender Systems

ISBN

979-8-4007-0505-2

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

1102-1107

Název nakladatele

Association for Computing Machinery

Místo vydání

New York, NY, United States

Místo konání akce

Bari, Italy

Datum konání akce

14. 9. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—