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.

翻译：超长查询与文档检索是信息检索中公认的具有挑战性的任务，通常被称为“按文档查询”（Query-by-Document, QBD）检索。以往研究表明，专门设计用于处理长输入序列的Transformer模型在QBD任务中并未展现出高效性。我们提出了一种基于新型比例相关性得分（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得分。大量评估结果显示，在五个不同数据集上，RPRS取得了显著优于现有最优模型的结果。此外，RPRS具有极高的效率，因为所有文档可在查询前完成预处理、嵌入和索引，这使得我们的重排序器复杂度仅为O(N)，其中N为查询和候选文档中的句子总数。更进一步，该方法解决了QBD检索任务中低资源训练的问题——它无需大量训练数据，仅需在有限范围内优化三个参数，即使只有少量标注数据，也可通过网格搜索完成优化。我们的详细分析表明，RPRS因覆盖了候选文档与查询的完整长度而获益。