Pre-trained transformer models, such as BERT and T5, have shown to be highly effective at
ad hoc passage and document ranking. Due to the inherent sequence length limits of these …

The information retrieval community has recently witnessed a revolution due to large
pretrained transformer models. Another key ingredient for this revolution was the MS …

The MS MARCO ranking dataset has been widely used for training deep learning models for
IR tasks, achieving considerable effectiveness on diverse zero-shot scenarios. However, this …

This work explores a framework for fact verification that leverages pretrained sequence-to-
sequence transformer models for sentence selection and label prediction, two key sub-tasks …

While much recent work has demonstrated that hard negative mining can be used to train
better bi-encoder models, few have considered it in the context of cross-encoders, which are …

Recent work has shown that small distilled language models are strong competitors to
models that are orders of magnitude larger and slower in a wide range of information …

Bi-encoders and cross-encoders are widely used in many state-of-the-art retrieval pipelines.
In this work we study the generalization ability of these two types of architectures on a wide …

In this work, we propose an effective multi-stage neural ranking system for the clinical trial
matching problem. First, we introduce NQS, a neural query synthesis method that leverages …

With doc2query, we train a neural sequence-to-sequence model that, given an input span of
text, predicts a natural language query that the text might answer. These predictions can be …

Recent work has shown that language models scaled to billions of parameters, such as GPT-
3, perform remarkably well in zero-shot and few-shot scenarios. In this work, we experiment …