论文标题
评估信息检索的生成对抗框架
Evaluating a Generative Adversarial Framework for Information Retrieval
论文作者
论文摘要
生成对抗网络（GAN）的最新进展已导致其广泛的应用程序到多个领域。最近的模型Irgan将该框架应用于信息检索（IR），并在过去几年中引起了极大的关注。在这项重点工作中，我们批判性地分析了Irgan的多个组成部分，同时提供了其某些缺点的实验和理论证据。具体而言，我们在策略梯度优化中确定了具有恒定基线术语的问题，并表明发电机会损害Irgan的性能。在我们的发现中，我们提出了两个受自对比度估计和共同训练影响的模型，在考虑的三个任务中，这两个模型都超过了Irgan。
Recent advances in Generative Adversarial Networks (GANs) have resulted in its widespread applications to multiple domains. A recent model, IRGAN, applies this framework to Information Retrieval (IR) and has gained significant attention over the last few years. In this focused work, we critically analyze multiple components of IRGAN, while providing experimental and theoretical evidence of some of its shortcomings. Specifically, we identify issues with the constant baseline term in the policy gradients optimization and show that the generator harms IRGAN's performance. Motivated by our findings, we propose two models influenced by self-contrastive estimation and co-training which outperform IRGAN on two out of the three tasks considered.
