当前位置:
X-MOL 学术
›
arXiv.cs.IR
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Retrieving Complex Tables with Multi-Granular Graph Representation Learning
arXiv - CS - Information Retrieval Pub Date : 2021-05-04 , DOI: arxiv-2105.01736 Fei Wang, Kexuan Sun, Muhao Chen, Jay Pujara, Pedro Szekely
arXiv - CS - Information Retrieval Pub Date : 2021-05-04 , DOI: arxiv-2105.01736 Fei Wang, Kexuan Sun, Muhao Chen, Jay Pujara, Pedro Szekely
The task of natural language table retrieval (NLTR) seeks to retrieve
semantically relevant tables based on natural language queries. Existing
learning systems for this task often treat tables as plain text based on the
assumption that tables are structured as dataframes. However, tables can have
complex layouts which indicate diverse dependencies between subtable
structures, such as nested headers. As a result, queries may refer to different
spans of relevant content that is distributed across these structures.
Moreover, such systems fail to generalize to novel scenarios beyond those seen
in the training set. Prior methods are still distant from a generalizable
solution to the NLTR problem, as they fall short in handling complex table
layouts or queries over multiple granularities. To address these issues, we
propose Graph-based Table Retrieval (GTR), a generalizable NLTR framework with
multi-granular graph representation learning. In our framework, a table is
first converted into a tabular graph, with cell nodes, row nodes and column
nodes to capture content at different granularities. Then the tabular graph is
input to a Graph Transformer model that can capture both table cell content and
the layout structures. To enhance the robustness and generalizability of the
model, we further incorporate a self-supervised pre-training task based on
graph-context matching. Experimental results on two benchmarks show that our
method leads to significant improvements over the current state-of-the-art
systems. Further experiments demonstrate promising performance of our method on
cross-dataset generalization, and enhanced capability of handling complex
tables and fulfilling diverse query intents. Code and data are available at
https://github.com/FeiWang96/GTR.
中文翻译:
使用多粒度图表示学习检索复杂表
自然语言表检索(NLTR)的任务是基于自然语言查询来检索语义相关的表。现有的用于该任务的学习系统通常基于表被构造为数据帧的假设,将表视为纯文本。但是,表可以具有复杂的布局,这些布局指示子表结构(例如嵌套标头)之间的不同依赖关系。结果,查询可以引用跨这些结构分布的相关内容的不同范围。而且,这样的系统无法推广到超出训练集中的新颖场景。先前的方法与NLTR问题的通用解决方案仍然相距甚远,因为它们在处理复杂的表布局或在多个粒度上进行查询方面均达不到要求。为了解决这些问题,我们提出了基于图的表检索(GTR),这是一种具有多粒度图表示学习的通用化NLTR框架。在我们的框架中,首先将表转换为表格图,其中具有单元节点,行节点和列节点以不同的粒度捕获内容。然后,将表格图表输入到Graph Transformer模型中,该模型可以捕获表格单元格内容和布局结构。为了增强模型的鲁棒性和通用性,我们进一步结合了基于图-上下文匹配的自我监督预训练任务。在两个基准上的实验结果表明,我们的方法导致了对当前最先进系统的显着改进。进一步的实验证明了我们的方法在跨数据集概括方面的有希望的性能,以及增强的处理复杂表和满足各种查询意图的能力。代码和数据位于https://github.com/FeiWang96/GTR。
更新日期:2021-05-06
中文翻译:
使用多粒度图表示学习检索复杂表
自然语言表检索(NLTR)的任务是基于自然语言查询来检索语义相关的表。现有的用于该任务的学习系统通常基于表被构造为数据帧的假设,将表视为纯文本。但是,表可以具有复杂的布局,这些布局指示子表结构(例如嵌套标头)之间的不同依赖关系。结果,查询可以引用跨这些结构分布的相关内容的不同范围。而且,这样的系统无法推广到超出训练集中的新颖场景。先前的方法与NLTR问题的通用解决方案仍然相距甚远,因为它们在处理复杂的表布局或在多个粒度上进行查询方面均达不到要求。为了解决这些问题,我们提出了基于图的表检索(GTR),这是一种具有多粒度图表示学习的通用化NLTR框架。在我们的框架中,首先将表转换为表格图,其中具有单元节点,行节点和列节点以不同的粒度捕获内容。然后,将表格图表输入到Graph Transformer模型中,该模型可以捕获表格单元格内容和布局结构。为了增强模型的鲁棒性和通用性,我们进一步结合了基于图-上下文匹配的自我监督预训练任务。在两个基准上的实验结果表明,我们的方法导致了对当前最先进系统的显着改进。进一步的实验证明了我们的方法在跨数据集概括方面的有希望的性能,以及增强的处理复杂表和满足各种查询意图的能力。代码和数据位于https://github.com/FeiWang96/GTR。