ECLIPSE: Contrastive Dimension Importance Estimation with Pseudo-Irrelevance Feedback for Dense Retrieval
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_ | 1866912161409794048 |
|---|---|
| author | D'Erasmo, Giulio Trappolini, Giovanni Tonellotto, Nicola Silvestri, Fabrizio |
| author_facet | D'Erasmo, Giulio Trappolini, Giovanni Tonellotto, Nicola Silvestri, Fabrizio |
| contents | Recent advances in Information Retrieval have leveraged high-dimensional embedding spaces to improve the retrieval of relevant documents. Moreover, the Manifold Clustering Hypothesis suggests that despite these high-dimensional representations, documents relevant to a query reside on a lower-dimensional, query-dependent manifold. While this hypothesis has inspired new retrieval methods, existing approaches still face challenges in effectively separating non-relevant information from relevant signals. We propose a novel methodology that addresses these limitations by leveraging information from both relevant and non-relevant documents. Our method, ECLIPSE, computes a centroid based on irrelevant documents as a reference to estimate noisy dimensions present in relevant ones, enhancing retrieval performance. Extensive experiments on three in-domain and one out-of-domain benchmarks demonstrate an average improvement of up to 19.50% (resp. 22.35%) in mAP(AP) and 11.42% (resp. 13.10%) in nDCG@10 w.r.t. the DIME-based baseline (resp. the baseline using all dimensions). Our results pave the way for more robust, pseudo-irrelevance-based retrieval systems in future IR research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_14967 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ECLIPSE: Contrastive Dimension Importance Estimation with Pseudo-Irrelevance Feedback for Dense Retrieval D'Erasmo, Giulio Trappolini, Giovanni Tonellotto, Nicola Silvestri, Fabrizio Information Retrieval Recent advances in Information Retrieval have leveraged high-dimensional embedding spaces to improve the retrieval of relevant documents. Moreover, the Manifold Clustering Hypothesis suggests that despite these high-dimensional representations, documents relevant to a query reside on a lower-dimensional, query-dependent manifold. While this hypothesis has inspired new retrieval methods, existing approaches still face challenges in effectively separating non-relevant information from relevant signals. We propose a novel methodology that addresses these limitations by leveraging information from both relevant and non-relevant documents. Our method, ECLIPSE, computes a centroid based on irrelevant documents as a reference to estimate noisy dimensions present in relevant ones, enhancing retrieval performance. Extensive experiments on three in-domain and one out-of-domain benchmarks demonstrate an average improvement of up to 19.50% (resp. 22.35%) in mAP(AP) and 11.42% (resp. 13.10%) in nDCG@10 w.r.t. the DIME-based baseline (resp. the baseline using all dimensions). Our results pave the way for more robust, pseudo-irrelevance-based retrieval systems in future IR research. |
| title | ECLIPSE: Contrastive Dimension Importance Estimation with Pseudo-Irrelevance Feedback for Dense Retrieval |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2412.14967 |