arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.01200cs.IR
收藏

使用 RPRS 进行极长查询和文档检索:一种高效且有效的基于 Transformer 的重排序器

Retrieval for Extremely Long Queries and Documents with RPRS: a Highly Efficient and Effective Transformer-based Re-Ranker

Arian Askari, Suzan Verberne, Amin Abolghasemi, Wessel Kraaij, Gabriella Pasi

AI总结:

针对极长查询与文档的 QBD 检索,本文提出基于比例相关性分数的 Transformer 重排序器 RPRS,以 O(N) 复杂度在五个数据集上超过最先进方法,并仅需少量标注数据调优三个参数。

摘要:

处理极长查询和文档的检索是信息检索中一项众所周知且具有挑战性的任务,通常被称为 Query-by-Document(QBD,文档查询)检索。在以往工作中,专门设计用于处理长输入序列的 Transformer 模型并未在 QBD 任务中表现出很高的有效性。我们提出一种基于新型比例相关性分数(Proportional Relevance Score,RPRS)的重排序器,用于计算查询与 top-k 候选文档之间的相关性分数。大量评估表明,RPRS 在五个不同数据集上取得了显著优于最先进模型的结果。此外,RPRS 非常高效,因为所有文档都可以在查询时间之前进行预处理、嵌入和索引,这使我们的重排序器具有 O(N) 复杂度的优势,其中 N 是查询和候选文档中的句子总数。此外,我们的方法解决了 QBD 检索任务中的低资源训练问题,因为它不需要大量训练数据,并且只有三个范围有限的参数;即使只有少量标注数据可用,也可以通过网格搜索对这些参数进行优化。我们的详细分析表明,RPRS 受益于覆盖候选文档和查询的完整长度。

英文摘要:

Retrieval with extremely long queries and documents is a well-known and challenging task in information retrieval and is commonly known as Query-by-Document (QBD) retrieval. Specifically designed Transformer models that can handle long input sequences have not shown high effectiveness in QBD tasks in previous work. We propose a Re-Ranker based on the novel Proportional Relevance Score (RPRS) to compute the relevance score between a query and the top-k candidate documents. Our extensive evaluation shows RPRS obtains significantly better results than the state-of-the-art models on five different datasets. Furthermore, RPRS is highly efficient since all documents can be pre-processed, embedded, and indexed before query time which gives our re-ranker the advantage of having a complexity of O(N) where N is the total number of sentences in the query and candidate documents. Furthermore, our method solves the problem of the low-resource training in QBD retrieval tasks as it does not need large amounts of training data, and has only three parameters with a limited range that can be optimized with a grid search even if a small amount of labeled data is available. Our detailed analysis shows that RPRS benefits from covering the full length of candidate documents and queries.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑