The distillation of ranking models has become an important topic in both...
Popularized by the Differentiable Search Index, the emerging paradigm of...
Query expansion is a widely used technique to improve the recall of sear...
Domain adaptation aims to transfer the knowledge acquired by models trai...
Recently, substantial progress has been made in text ranking based on
pr...
Retrieval augmentation has shown promising improvements in different tas...
State-of-the-art neural models typically encode document-query pairs usi...
Multiclass classification (MCC) is a fundamental machine learning proble...
We introduce Born Again neural Rankers (BAR) in the Learning to Rank (LT...
The goal of model distillation is to faithfully transfer teacher model
k...
Education has a significant impact on both society and personal life. Wi...
In this paper, we report the results of our participation in the TREC-CO...
We study a variant of the thresholding bandit problem (TBP) in the conte...
Interpretability of learning-to-rank models is a crucial yet relatively
...
In personal email search, user queries often impose different requiremen...
Unsupervised text embedding has shown great power in a wide range of NLP...