DESIRE-ME: Domain-Enhanced Supervised Information REtrieval using Mixture-of-Experts
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913274575978496 |
|---|---|
| author | Kasela, Pranav Pasi, Gabriella Perego, Raffaele Tonellotto, Nicola |
| author_facet | Kasela, Pranav Pasi, Gabriella Perego, Raffaele Tonellotto, Nicola |
| contents | Open-domain question answering requires retrieval systems able to cope with the diverse and varied nature of questions, providing accurate answers across a broad spectrum of query types and topics. To deal with such topic heterogeneity through a unique model, we propose DESIRE-ME, a neural information retrieval model that leverages the Mixture-of-Experts framework to combine multiple specialized neural models. We rely on Wikipedia data to train an effective neural gating mechanism that classifies the incoming query and that weighs the predictions of the different domain-specific experts correspondingly. This allows DESIRE-ME to specialize adaptively in multiple domains. Through extensive experiments on publicly available datasets, we show that our proposal can effectively generalize domain-enhanced neural models. DESIRE-ME excels in handling open-domain questions adaptively, boosting by up to 12% in NDCG@10 and 22% in P@1, the underlying state-of-the-art dense retrieval model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_13468 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DESIRE-ME: Domain-Enhanced Supervised Information REtrieval using Mixture-of-Experts Kasela, Pranav Pasi, Gabriella Perego, Raffaele Tonellotto, Nicola Information Retrieval Open-domain question answering requires retrieval systems able to cope with the diverse and varied nature of questions, providing accurate answers across a broad spectrum of query types and topics. To deal with such topic heterogeneity through a unique model, we propose DESIRE-ME, a neural information retrieval model that leverages the Mixture-of-Experts framework to combine multiple specialized neural models. We rely on Wikipedia data to train an effective neural gating mechanism that classifies the incoming query and that weighs the predictions of the different domain-specific experts correspondingly. This allows DESIRE-ME to specialize adaptively in multiple domains. Through extensive experiments on publicly available datasets, we show that our proposal can effectively generalize domain-enhanced neural models. DESIRE-ME excels in handling open-domain questions adaptively, boosting by up to 12% in NDCG@10 and 22% in P@1, the underlying state-of-the-art dense retrieval model. |
| title | DESIRE-ME: Domain-Enhanced Supervised Information REtrieval using Mixture-of-Experts |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2403.13468 |