An important goal of online platforms is to enable content discovery, i....
A number of learned sparse and dense retrieval approaches have recently ...
Ranking responses for a given dialogue context is a popular benchmark in...
Heavily pre-trained transformers for language modelling, such as BERT, h...
According to the Probability Ranking Principle (PRP), ranking documents ...
We study Label Smoothing (LS), a widely used regularization technique, i...
Understanding when and why neural ranking models fail for an IR task via...
Heavily pre-trained transformer models such as BERT have recently shown ...
Neural ranking models are traditionally trained on a series of random
ba...
Conversational search is an approach to information retrieval (IR), wher...