Natural Language Question Answering over RDF — A Graph Data Driven Approach论文学习

研究内容

  • In this paper, we propose a systematic framework to answer natural language questions over RDF repository (RDF Q/A) from a graph data-driven perspective. (在本文中,我们提出了一个系统的框架,从图数据驱动的角度来回答RDF存储库(RDF Q/ a)上的自然语言问题。

技术方案

  • Generally speaking, there are offline and online phases in our solution.(一般来说,在我们的解决方案中有离线和在线阶段。
    • In the offline processing, we propose a graph mining algorithm to map natural language phrases to top-k possible predicates (in a RDF dataset) to form a paraphrase dictionaryD, which is used for question understanding in RDF Q/A.(在离线处理中,我们提出了一种图挖掘算法,将自然语言短语映射到 top-k 可能的谓词(在 RDF 数据集中)形成释义词典 D,用于 RDF Q/A 中的问题理解。
    • In the online processing, we adopt two-stage approach. In the query understanding stage, we propose a semantic query graph to model the query intention in the natural language question in a structural way. Then, RDF Q/A is reduced to subgraph matching problem in the query evaluation stage. We resolve the ambiguity at the time when matches of the query are found. The cost of disambiguation is saved if there are no matching found.(在在线处理中,我们采用两阶段的方法。 在查询理解阶段,我们提出了一个语义查询图,以结构化的方式对自然语言问题中的查询意图进行建模。 然后,RDF Q/A 在查询评估阶段被简化为子图匹配问题。 我们在找到查询匹配项时解决歧义。 如果找不到匹配项,则可以节省消歧成本。
    • We take a lazy approach and push down the disambiguation to the query evaluation stage. (我们采用一种懒惰的方法,将消歧向下推到查询评估阶段

如何做实验

  • We compare our method with one state-of-the-art algorithm DEANNA and all systems in QALD-3 competition on DBpedia RDF dataset.(我们在 DBpedia RDF 数据集上将我们的方法与一种最先进的算法 DEANNA 和 QALD-3 竞赛中的所有系统进行比较。
  • To build the paraphrase dictionary, we use two different relation phrase datasets in Patty system, wordnet-wikipedia and freebase-wikipediawe.(为了构建释义词典,我们使用了Patty系统中两种不同的关系短语数据集。
posted @ 2021-10-20 14:01  bky-16  阅读(83)  评论(0编辑  收藏  举报