Semi-structured data is a text that has been organized by subject or topic or that fits into a hierarchical programming language. Still, the text within is open-ended and lacks structure. Emails, for example, are semi-structured by Recipient, Sender, Date, Subject, and so on, or are automatically classified into folders such as Outbox, Inbox. The problem of QA over semi-structured data is that, given a query Qand a semi-structured data example S, return the QA match score d(Q;S), which predicts the likelihood that Sanswers Q. 3 Method In this section, we proposed GraSSLM, which is a graph model of semi-structured data on the Web for QA. Figure 3 shows the overall structure of GraSSLM.