论文标题
与预训练的变形金刚一起稀疏成对重新排行
Sparse Pairwise Re-ranking with Pre-trained Transformers
论文作者
论文摘要
成对重新排列模型预测两个文档中的哪个与查询更相关，然后从此类偏好中汇总了最终排名。这通常比直接预测每个文档的相关价值的重新排列模型更有效。但是，成对模型的高推断开销限制了其实际应用：通常，对于要重新排名的一组$ k $文档，所有$ k^2-k $比较对的偏好是不包括自我镜头的所有比较对。我们研究了通过从所有对采样来提高成对重新排列的效率。在一项探索性研究中，我们评估了三种抽样方法和五种偏好聚集方法。最佳组合可以在可接受的检索效率丧失时进行比较的数量级，而在比较的大约三分之一的情况下，已经实现了竞争有效性。
Pairwise re-ranking models predict which of two documents is more relevant to a query and then aggregate a final ranking from such preferences. This is often more effective than pointwise re-ranking models that directly predict a relevance value for each document. However, the high inference overhead of pairwise models limits their practical application: usually, for a set of $k$ documents to be re-ranked, preferences for all $k^2-k$ comparison pairs excluding self-comparisons are aggregated. We investigate whether the efficiency of pairwise re-ranking can be improved by sampling from all pairs. In an exploratory study, we evaluate three sampling methods and five preference aggregation methods. The best combination allows for an order of magnitude fewer comparisons at an acceptable loss of retrieval effectiveness, while competitive effectiveness is already achieved with about one third of the comparisons.
