From Easy to Hard: A Dual Curriculum Learning Framework for Context-Aware Document Ranking

TL;DR

This paper introduces a curriculum learning framework that gradually trains context-aware document ranking models from easy to hard examples, significantly improving performance on real query log datasets.

Contribution

It proposes a novel dual curriculum learning approach for context-aware document ranking, guiding models from simple to complex examples to enhance effectiveness.

Findings

Improved ranking performance on real datasets

Effective use of positive and negative examples in curricula

Significant performance gains over baseline methods

Abstract

Contextual information in search sessions is important for capturing users' search intents. Various approaches have been proposed to model user behavior sequences to improve document ranking in a session. Typically, training samples of (search context, document) pairs are sampled randomly in each training epoch. In reality, the difficulty to understand user's search intent and to judge document's relevance varies greatly from one search context to another. Mixing up training samples of different difficulties may confuse the model's optimization process. In this work, we propose a curriculum learning framework for context-aware document ranking, in which the ranking model learns matching signals between the search context and the candidate document in an easy-to-hard manner. In so doing, we aim to guide the model gradually toward a global optimum. To leverage both positive and negative examples, two curricula are designed. Experiments on two real query log datasets show that our proposed framework can improve the performance of several existing methods significantly, demonstrating the effectiveness of curriculum learning for context-aware document ranking.