Incorporating Multimodal Information in Open-Domain Web Keyphrase Extraction
Incorporating Multimodal Information in Open-Domain Web Keyphrase Extraction
复制标题
DOI：
10.18653/v1/2020.emnlp-main.140
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Yansen Wang;Zhenhua Fan;C. Rosé
中科院分区：
文献类型：
--
作者：
Yansen Wang;Zhenhua Fan;C. Rosé
Web上的开放领域关键词抽取是一项基本而复杂的自然语言处理任务，在信息检索领域有着广泛的实际应用。与其他文档类型不同，网页设计旨在方便导航和查找信息。有效的设计在布局和格式化信号中进行编码，这些信号指向可以找到重要信息的位置。在这项工作中，我们提出了一种利用这些多模式信号来帮助完成KPE任务的建模方法。特别是，我们在微观层面利用词汇和视觉特征(例如，大小、字体、位置)来实现有效的策略归纳和在宏观层面描述页面的元级特征，以帮助进行策略选择。我们的评估表明，在KPE任务中，这种方法结合了有效的策略归纳和策略选择，性能优于最先进的模型。定性的事后分析说明了这些功能如何在模型中发挥作用。
Open-domain Keyphrase extraction (KPE) on the Web is a fundamental yet complex NLP task with a wide range of practical applications within the field of Information Retrieval. In contrast to other document types, web page designs are intended for easy navigation and information finding. Effective designs encode within the layout and formatting signals that point to where the important information can be found. In this work, we propose a modeling approach that leverages these multi-modal signals to aid in the KPE task. In particular, we leverage both lexical and visual features (e.g., size, font, position) at the micro-level to enable effective strategy induction and meta-level features that describe pages at a macro-level to aid in strategy selection. Our evaluation demonstrates that a combination of effective strategy induction and strategy selection within this approach for the KPE task outperforms state-of-the-art models. A qualitative post-hoc analysis illustrates how these features function within the model.