arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.06162cs.CL
收藏

基于中间问题分解的SPARQLing数据库查询

SPARQLing Database Queries from Intermediate Question Decompositions

HSE University(高等经济大学);Yandex(杨德克斯)

Irina Saparina, Anton Osokin

摘要:

为了将自然语言问题转换为可执行的数据库查询,大多数方法依赖于完全注释的训练集。使用查询注释大型数据集是困难的,因为它需要查询语言专业知识。我们减少这种负担,使用接地在数据库中间的问题表示。这些表示更容易收集,并且最初在Break数据集中众包(Wolfson等人,2020年)。我们的管道由两部分组成:一个神经语义解析器,它将自然语言问题转换为中间表示和一个不可训练的转译器SPARQL查询语言(一种访问知识图谱和语义Web的标准语言)。我们选择SPARQL是因为它的查询在结构上更接近我们的中间表示(与SQL相比)。我们观察到,我们的模型在具有挑战性的Spider数据集上构建的查询的执行准确性与使用注释SQL查询训练的最先进的文本到SQL方法相当。我们的代码和数据是公开的(请参阅https://github.com/yandex-research/sparqling-queries)。

英文摘要:

To translate natural language questions into executable database queries, most approaches rely on a fully annotated training set. Annotating a large dataset with queries is difficult as it requires query-language expertise. We reduce this burden using grounded in databases intermediate question representations. These representations are simpler to collect and were originally crowdsourced within the Break dataset (Wolfson et al., 2020). Our pipeline consists of two parts: a neural semantic parser that converts natural language questions into the intermediate representations and a non-trainable transpiler to the SPARQL query language (a standard language for accessing knowledge graphs and semantic web). We chose SPARQL because its queries are structurally closer to our intermediate representations (compared to SQL). We observe that the execution accuracy of queries constructed by our model on the challenging Spider dataset is comparable with the state-of-the-art text-to-SQL methods trained with annotated SQL queries. Our code and data are publicly available (see https://github.com/yandex-research/sparqling-queries).

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。

↑