Web question answering with neurosymbolic program synthesis
Web question answering with neurosymbolic program synthesis
复制标题
DOI：
10.1145/3453483.3454047
复制
发表时间：
2021-04
期刊：
影响因子：
--
通讯作者：
Qiaochu Chen;Aaron Lamoreaux;Xinyu Wang;Greg Durrett;O. Bastani;Işıl Dillig
中科院分区：
文献类型：
--
作者：
Qiaochu Chen;Aaron Lamoreaux;Xinyu Wang;Greg Durrett;O. Bastani;Işıl Dillig
在本文中，我们提出了一种新的技术，基于程序合成的网页信息提取。给定一个自然语言查询和一些标记的网页，我们的方法合成一个程序，可以用来提取类似类型的信息，从其他未标记的网页。为了处理具有不同结构的网站，我们的方法采用了神经符号DSL，该DSL结合了神经NLP模型以及用于树导航和字符串操作的标准语言结构。我们还提出了一个最佳的合成算法，生成所有的DSL程序，达到最佳的F1分数的训练样本。我们的合成技术是合成的，修剪搜索空间，利用DSL的单调性，并使用转导学习选择具有良好的泛化能力的程序。我们已经在一个名为WebQA的新工具中实现了这些想法，并在多个领域的25个不同任务中对其进行了评估。我们的实验表明，WebQA显着优于现有的工具，如国家的最先进的问答模型和包装归纳系统。
In this paper, we propose a new technique based on program synthesis for extracting information from webpages. Given a natural language query and a few labeled webpages, our method synthesizes a program that can be used to extract similar types of information from other unlabeled webpages. To handle websites with diverse structure, our approach employs a neurosymbolic DSL that incorporates both neural NLP models as well as standard language constructs for tree navigation and string manipulation. We also propose an optimal synthesis algorithm that generates all DSL programs that achieve optimal F1 score on the training examples. Our synthesis technique is compositional, prunes the search space by exploiting a monotonicity property of the DSL, and uses transductive learning to select programs with good generalization power. We have implemented these ideas in a new tool called WebQA and evaluate it on 25 different tasks across multiple domains. Our experiments show that WebQA significantly outperforms existing tools such as state-of-the-art question answering models and wrapper induction systems.