Train Once, Use Flexibly: A Modular Framework for Multi-Aspect Neural News Recommendation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Iana, Andreea, Glavaš, Goran, Paulheim, Heiko
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910614891266048
author Iana, Andreea
Glavaš, Goran
Paulheim, Heiko
author_facet Iana, Andreea
Glavaš, Goran
Paulheim, Heiko
contents Recent neural news recommenders (NNRs) extend content-based recommendation (1) by aligning additional aspects (e.g., topic, sentiment) between candidate news and user history or (2) by diversifying recommendations w.r.t. these aspects. This customization is achieved by ``hardcoding`` additional constraints into the NNR's architecture and/or training objectives: any change in the desired recommendation behavior thus requires retraining the model with a modified objective. This impedes widespread adoption of multi-aspect news recommenders. In this work, we introduce MANNeR, a modular framework for multi-aspect neural news recommendation that supports on-the-fly customization over individual aspects at inference time. With metric-based learning as its backbone, MANNeR learns aspect-specialized news encoders and then flexibly and linearly combines the resulting aspect-specific similarity scores into different ranking functions, alleviating the need for ranking function-specific retraining of the model. Extensive experimental results show that MANNeR consistently outperforms state-of-the-art NNRs on both standard content-based recommendation and single- and multi-aspect customization. Lastly, we validate that MANNeR's aspect-customization module is robust to language and domain transfer.
format Preprint
id arxiv_https___arxiv_org_abs_2307_16089
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Train Once, Use Flexibly: A Modular Framework for Multi-Aspect Neural News Recommendation
Iana, Andreea
Glavaš, Goran
Paulheim, Heiko
Information Retrieval
H.3.3; I.2.7
Recent neural news recommenders (NNRs) extend content-based recommendation (1) by aligning additional aspects (e.g., topic, sentiment) between candidate news and user history or (2) by diversifying recommendations w.r.t. these aspects. This customization is achieved by ``hardcoding`` additional constraints into the NNR's architecture and/or training objectives: any change in the desired recommendation behavior thus requires retraining the model with a modified objective. This impedes widespread adoption of multi-aspect news recommenders. In this work, we introduce MANNeR, a modular framework for multi-aspect neural news recommendation that supports on-the-fly customization over individual aspects at inference time. With metric-based learning as its backbone, MANNeR learns aspect-specialized news encoders and then flexibly and linearly combines the resulting aspect-specific similarity scores into different ranking functions, alleviating the need for ranking function-specific retraining of the model. Extensive experimental results show that MANNeR consistently outperforms state-of-the-art NNRs on both standard content-based recommendation and single- and multi-aspect customization. Lastly, we validate that MANNeR's aspect-customization module is robust to language and domain transfer.
title Train Once, Use Flexibly: A Modular Framework for Multi-Aspect Neural News Recommendation
topic Information Retrieval
H.3.3; I.2.7
url https://arxiv.org/abs/2307.16089