arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.08705cs.IR
收藏

评估模型集成在段落检索神经重新排序中的优势

Assessing the Benefits of Model Ensembles in Neural Re-Ranking for Passage Retrieval

Luís Borges, Bruno Martins, Jamie Callan

摘要:

我们的工作旨在通过实验评估神经方法的背景下,通过重新排序的模型集成的好处。从相对标准的神经模型开始,我们使用一种名为快速几何集成的先前技术来从特定的训练时间表生成多个模型实例,然后将注意力集中在用于组合来自多个模型实例的结果的不同类型的方法上(例如,平均排序分数、使用来自IR文献的融合方法、或使用监督学习排序)。使用MS-MARCO数据集的测试表明,模型集成确实可以提高排名质量,特别是在监督学习-to-rank的情况下,尽管也有无监督的排名聚合。

英文摘要:

Our work aimed at experimentally assessing the benefits of model ensembling within the context of neural methods for passage reranking. Starting from relatively standard neural models, we use a previous technique named Fast Geometric Ensembling to generate multiple model instances from particular training schedules, then focusing or attention on different types of approaches for combining the results from the multiple model instances (e.g., averaging the ranking scores, using fusion methods from the IR literature, or using supervised learning-to-rank). Tests with the MS-MARCO dataset show that model ensembling can indeed benefit the ranking quality, particularly with supervised learning-to-rank although also with unsupervised rank aggregation.

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。

↑