17 citations · 21 across the 4 of their papers we have counts for
6 papers · 1 filter
Sparse and Dense Approaches for the Full-rank Retrieval of Responses for Dialogues
Gustavo Penha, Claudia Hauff
Ranking responses for a given dialogue context is a popular benchmark in which the setup is to re-rank the ground-truth response over a limited set of responses, where is t…
On the Calibration and Uncertainty of Neural Learning to Rank Models
Gustavo Penha, Claudia Hauff
According to the Probability Ranking Principle (PRP), ranking documents in decreasing order of their probability of relevance leads to an optimal document ranking for ad-hoc retrie…
Weakly Supervised Label Smoothing
Gustavo Penha, Claudia Hauff
We study Label Smoothing (LS), a widely used regularization technique, in the context of neural learning to rank (L2R) models. LS combines the ground-truth labels with a uniform di…
Slice-Aware Neural Ranking
Gustavo Penha, Claudia Hauff
Understanding when and why neural ranking models fail for an IR task via error analysis is an important part of the research cycle. Here we focus on the challenges of (i) identifyi…
What does BERT know about books, movies and music? Probing BERT for Conversational Recommendation
Gustavo Penha, Claudia Hauff
Heavily pre-trained transformer models such as BERT have recently shown to be remarkably powerful at language modelling by achieving impressive results on numerous downstream tasks…
Curriculum Learning Strategies for IR: An Empirical Study on Conversation Response Ranking
Gustavo Penha, Claudia Hauff
Neural ranking models are traditionally trained on a series of random batches, sampled uniformly from the entire training set. Curriculum learning has recently been shown to improv…