用于Web可传递属性提取的简化DOM树
Simplified DOM Trees for Transferable Attribute Extraction from the Web
摘要：
一直有一个稳定的需要，精确地提取结构化的知识，从网络（即HTML文档）。给定一个网页，提取结构化对象以及各种感兴趣的属性（例如，价格，出版商，作者和书籍的流派）可以促进各种下游应用，例如大规模知识库构建，电子商务产品搜索和个性化推荐。考虑到每个网页都是从HTML DOM树中渲染出来的，现有的方法将问题描述为DOM树节点标记任务。然而，它们要么依赖于计算上昂贵的视觉特征工程，要么无法对树节点之间的关系进行建模。在本文中，我们提出了一种新的可转移的方法，简化的DOM树属性提取（DOM），有效地检索有用的上下文为每个节点，利用树结构来解决这个问题。我们研究了两个具有挑战性的实验设置：（i）垂直内的Few-Shot提取，和（ii）跨垂直的fewshot提取领域外的知识，以评估我们的方法。在SWDE公共数据集上进行的大量实验表明，在F1得分上，RSDOM比最先进的（SOTA）方法高出1.44%。我们还发现，利用来自不同垂直（垂直交叉提取）的知识是非常有用的，并有助于进一步击败SOTA 1.37%。
英文摘要：
There has been a steady need to precisely extract structured knowledge from the web (i.e. HTML documents). Given a web page, extracting a structured object along with various attributes of interest (e.g. price, publisher, author, and genre for a book) can facilitate a variety of downstream applications such as large-scale knowledge base construction, e-commerce product search, and personalized recommendation. Considering each web page is rendered from an HTML DOM tree, existing approaches formulate the problem as a DOM tree node tagging task. However, they either rely on computationally expensive visual feature engineering or are incapable of modeling the relationship among the tree nodes. In this paper, we propose a novel transferable method, Simplified DOM Trees for Attribute Extraction (SimpDOM), to tackle the problem by efficiently retrieving useful context for each node by leveraging the tree structure. We study two challenging experimental settings: (i) intra-vertical few-shot extraction, and (ii) cross-vertical fewshot extraction with out-of-domain knowledge, to evaluate our approach. Extensive experiments on the SWDE public dataset show that SimpDOM outperforms the state-of-the-art (SOTA) method by 1.44% on the F1 score. We also find that utilizing knowledge from a different vertical (cross-vertical extraction) is surprisingly useful and helps beat the SOTA by a further 1.37%.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
