研究內容

Given an RDF graph G and a natural language question qNL, our goal is to interpret qNL as a SPARQL query qS, by mapping the semantic items — relations(i.e. properties), entities and classes expressed by qNL to the corresponding triple patterns inqS.（給定一個 RDF 圖 G 和一個自然語言問題 qNL，我們的目標是將 qNL 解釋為一個 SPARQL 查詢 qS，通過將 qNL 表示的語義專案——關係（即屬性）、實體和類對映到相應的三重模式 inqS。

系統架構

the system framework is separated into offline and online two parts.

• Offline Processing: To enable semantic relation extraction in online processing, a dictionary of the RDF relations and their natural language paraphrases is automatically built in advance.（離線處理：為了能夠在線上處理中提取語義關係，預先自動構建 RDF 關係及其自然語言釋義的字典。
  ）
• During the online stage, the input question qNL is fed into the following four-step pipeline:（線上階段，輸入問題 qNL 被送入以下四步管道：）
  1. qNL is parsed into a dependency tree tNL.（qNL 被解析為依賴樹 tNL）
  2. the phrases in qNL that mention any semantic relation are recognized in tNL with the help of the paraphrase dictionary. （在釋義詞典的幫助下，在 tNL 中可以識別 qNL 中提到任何語義關係的短語。
     ）
  3. these phrases are mapped to the RDF fragments to find their matches of semantic items in the RDF graph G.（將這些短語對映到 RDF 片段以在 RDF 圖 G 中找到它們的語義項匹配。）
  4. the RDF fragments are joined to compute a reasonable subgraph of graph G, by checking their compatibility based on the dependency tree tNL.（通過基於依賴樹 tNL 檢查它們的相容性，連線 RDF 片段以計算圖 G 的合理子圖。）
  5. The results are ranked according to the score of semantic similarity and coherence, leading to the target SPARQL.（結果根據語義相似性和連貫性的分數進行排名，從而得出目標 SPARQL。）

如何做實驗

The system is implemented on DBpedia dataset.（該系統是在 DBpedia 資料集上實現的。）