Modeling Label Ambiguity for Neural List-Wise Learning to Rank

TL;DR

This paper introduces a novel sampling technique for list-wise learning to rank that explicitly models label ambiguity, leading to improved generalization and performance over existing methods.

Contribution

It proposes a new loss function that accounts for relevance label ambiguity in neural list-wise ranking models, enhancing ranking accuracy.

Findings

The new method outperforms ListNet and ListMLE on validation and test sets.

Model generalizes better with the proposed ambiguity-aware loss.

Significant performance improvements demonstrate the effectiveness of the approach.

Abstract

List-wise learning to rank methods are considered to be the state-of-the-art. One of the major problems with these methods is that the ambiguous nature of relevance labels in learning to rank data is ignored. Ambiguity of relevance labels refers to the phenomenon that multiple documents may be assigned the same relevance label for a given query, so that no preference order should be learned for those documents. In this paper we propose a novel sampling technique for computing a list-wise loss that can take into account this ambiguity. We show the effectiveness of the proposed method by training a 3-layer deep neural network. We compare our new loss function to two strong baselines: ListNet and ListMLE. We show that our method generalizes better and significantly outperforms other methods on the validation and test sets.