ReFIT: Relevance Feedback from a Reranker during Inference
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911890437832704 |
|---|---|
| author | Reddy, Revanth Gangi Dasigi, Pradeep Sultan, Md Arafat Cohan, Arman Sil, Avirup Ji, Heng Hajishirzi, Hannaneh |
| author_facet | Reddy, Revanth Gangi Dasigi, Pradeep Sultan, Md Arafat Cohan, Arman Sil, Avirup Ji, Heng Hajishirzi, Hannaneh |
| contents | Retrieve-and-rerank is a prevalent framework in neural information retrieval, wherein a bi-encoder network initially retrieves a pre-defined number of candidates (e.g., K=100), which are then reranked by a more powerful cross-encoder model. While the reranker often yields improved candidate scores compared to the retriever, its scope is confined to only the top K retrieved candidates. As a result, the reranker cannot improve retrieval performance in terms of Recall@K. In this work, we propose to leverage the reranker to improve recall by making it provide relevance feedback to the retriever at inference time. Specifically, given a test instance during inference, we distill the reranker's predictions for that instance into the retriever's query representation using a lightweight update mechanism. The aim of the distillation loss is to align the retriever's candidate scores more closely with those produced by the reranker. The algorithm then proceeds by executing a second retrieval step using the updated query vector. We empirically demonstrate that this method, applicable to various retrieve-and-rerank frameworks, substantially enhances retrieval recall across multiple domains, languages, and modalities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_11744 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | ReFIT: Relevance Feedback from a Reranker during Inference Reddy, Revanth Gangi Dasigi, Pradeep Sultan, Md Arafat Cohan, Arman Sil, Avirup Ji, Heng Hajishirzi, Hannaneh Information Retrieval Computation and Language Retrieve-and-rerank is a prevalent framework in neural information retrieval, wherein a bi-encoder network initially retrieves a pre-defined number of candidates (e.g., K=100), which are then reranked by a more powerful cross-encoder model. While the reranker often yields improved candidate scores compared to the retriever, its scope is confined to only the top K retrieved candidates. As a result, the reranker cannot improve retrieval performance in terms of Recall@K. In this work, we propose to leverage the reranker to improve recall by making it provide relevance feedback to the retriever at inference time. Specifically, given a test instance during inference, we distill the reranker's predictions for that instance into the retriever's query representation using a lightweight update mechanism. The aim of the distillation loss is to align the retriever's candidate scores more closely with those produced by the reranker. The algorithm then proceeds by executing a second retrieval step using the updated query vector. We empirically demonstrate that this method, applicable to various retrieve-and-rerank frameworks, substantially enhances retrieval recall across multiple domains, languages, and modalities. |
| title | ReFIT: Relevance Feedback from a Reranker during Inference |
| topic | Information Retrieval Computation and Language |
| url | https://arxiv.org/abs/2305.11744 |