A Hybrid Deep Model for Learning to Rank Data Tables
A Hybrid Deep Model for Learning to Rank Data Tables
复制标题
DOI：
10.1109/bigdata50022.2020.9378185
复制
发表时间：
2020-12
期刊：
影响因子：
--
通讯作者：
M. Trabelsi;Zhiyu Chen;Brian D. Davison;J. Heflin
中科院分区：
文献类型：
--
作者：
M. Trabelsi;Zhiyu Chen;Brian D. Davison;J. Heflin
我们通过一个新的神经架构，结合语义和相关性匹配的特设表检索的问题。理解表的结构化形式和查询标记之间的联系是信息检索中一个重要但被忽视的问题。我们使用一种学习排名的方法来训练系统，以捕获结构化形式的候选表和查询令牌之间的交互中的语义和相关性信号。卷积过滤器，从查询/表的交互提取上下文特征相结合的特征向量的基础上分布的查询和表之间的术语相似性。我们建议使用行和列摘要将表格内容合并到我们的新神经模型中。我们使用两个数据集来评估我们的方法，并且我们证明了在表检索和文档检索中的最先进方法的检索度量方面的实质性改进，以及从句子，文档和表类型分类适应表检索任务的神经架构。我们的消融研究支持的重要性，语义和相关性匹配的表检索。
We address the problem of ad hoc table retrieval via a new neural architecture that incorporates both semantic and relevance matching. Understanding the connection between the structured form of a table and query tokens is an important yet neglected problem in information retrieval. We use a learning- to-rank approach to train a system to capture semantic and relevance signals within interactions between the structured form of candidate tables and query tokens. Convolutional filters that extract contextual features from query/table interactions are combined with a feature vector based on the distributions of term similarity between queries and tables. We propose using row and column summaries to incorporate table content into our new neural model. We evaluate our approach using two datasets, and we demonstrate substantial improvements in terms of retrieval metrics over state-of-the-art methods in table retrieval and document retrieval, and neural architectures from sentence, document, and table type classification adapted to the table retrieval task. Our ablation study supports the importance of both semantic and relevance matching in the table retrieval.