Researchers have had much recent success with ranking models based on so-called
learned sparse representations generated by transformers. One crucial advantage of this …

We study ranked list truncation (RLT) from a novel retrieve-then-re-rank perspective, where
we optimize re-ranking by truncating the retrieved list (ie, trim re-ranking candidates). RLT is …

Understanding the behavior of deep neural networks for Information Retrieval (IR) is crucial
to improve trust in these effective models. Current popular approaches to diagnose the …

The ranking pipelines of modern search platforms commonly exploit complex machine-
learned models and have a significant impact on the query response time. In this paper, we …

Recommender systems in social media websites provide value to their communities by
recommending engaging content and meaningful connections. Scaling high-quality …

This paper presents ConvRerank, a conversational passage re-ranker that employs a newly
developed pseudo-labeling approach. Our proposed view-ensemble method enhances the …

Pretrained transformers have significantly advanced the field of information retrieval (IR)
since the introduction of BERT. Through unsupervised pretraining followed by task-aware …

The ever-increasing volume of web-based documents poses a challenge in efficiently
accessing specialized knowledge from domain-specific sources, requiring a profound …