Counterfactual Query Rewriting to Use Historical Relevance Feedback
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909480301625344 |
|---|---|
| author | Keller, Jüri Fröbe, Maik Hendriksen, Gijs Alexander, Daria Potthast, Martin Hagen, Matthias Schaer, Philipp |
| author_facet | Keller, Jüri Fröbe, Maik Hendriksen, Gijs Alexander, Daria Potthast, Martin Hagen, Matthias Schaer, Philipp |
| contents | When a retrieval system receives a query it has encountered before, previous relevance feedback, such as clicks or explicit judgments can help to improve retrieval results. However, the content of a previously relevant document may have changed, or the document might not be available anymore. Despite this evolved corpus, we counterfactually use these previously relevant documents as relevance signals. In this paper we proposed approaches to rewrite user queries and compare them against a system that directly uses the previous qrels for the ranking. We expand queries with terms extracted from the previously relevant documents or derive so-called keyqueries that rank the previously relevant documents to the top of the current corpus. Our evaluation in the CLEF LongEval scenario shows that rewriting queries with historical relevance feedback improves the retrieval effectiveness and even outperforms computationally expensive transformer-based approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_03891 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Counterfactual Query Rewriting to Use Historical Relevance Feedback Keller, Jüri Fröbe, Maik Hendriksen, Gijs Alexander, Daria Potthast, Martin Hagen, Matthias Schaer, Philipp Information Retrieval When a retrieval system receives a query it has encountered before, previous relevance feedback, such as clicks or explicit judgments can help to improve retrieval results. However, the content of a previously relevant document may have changed, or the document might not be available anymore. Despite this evolved corpus, we counterfactually use these previously relevant documents as relevance signals. In this paper we proposed approaches to rewrite user queries and compare them against a system that directly uses the previous qrels for the ranking. We expand queries with terms extracted from the previously relevant documents or derive so-called keyqueries that rank the previously relevant documents to the top of the current corpus. Our evaluation in the CLEF LongEval scenario shows that rewriting queries with historical relevance feedback improves the retrieval effectiveness and even outperforms computationally expensive transformer-based approaches. |
| title | Counterfactual Query Rewriting to Use Historical Relevance Feedback |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2502.03891 |