ViTOR：基于视觉特征的学习排序网页(CS IR)---Elva

网页的视觉外观包含了有关网页质量的有价值的信息，可用于提高学习排序（LTR）的性能。本文中我们介绍了视觉学习排序（ViTOR）模型，该模型通过（i）从预先训练的图像分类模型转移学习，以及（ii）从网页快照生成的合成显著热图，集成了最新的视觉特征提取方法。由于目前还没有针对具有视觉特性的LTR任务的公共数据集，因此我们还引入并发布了ViTOR数据集，其中包含视觉丰富和多样的网页。ViTOR数据集由可视快照、非可视特性和ClueWeb12网页和TREC Web跟踪查询的相关性判断组成。我们在ViTOR数据集上对所提出的ViTOR模型进行了实验，结果表明，该模型显著提高了具有视觉特征的LTR的性能。

原文题目：ViTOR: Learning to Rank Webpages Based on Visual Features

原文：The visual appearance of a webpage carries valuable information about its quality and can be used to improve the performance of learning to rank (LTR). We introduce the Visual learning TO Rank (ViTOR) model that integrates state-of-the-art visual features extraction methods by (i) transfer learning from a pre-trained image classification model, and (ii) synthetic saliency heat maps generated from webpage snapshots. Since there is currently no public dataset for the task of LTR with visual features, we also introduce and release the ViTOR dataset, containing visually rich and diverse webpages. The ViTOR dataset consists of visual snapshots, non-visual features and relevance judgments for ClueWeb12 webpages and TREC Web Track queries. We experiment with the proposed ViTOR model on the ViTOR dataset and show that it significantly improves the performance of LTR with visual features.

原文作者：Bram van den Akker, Ilya Markov, Maarten de Rijke

原文地址：https://arxiv.org/abs/1903.02939