NaLIR

A NaLIR is a Natural Language Database Interface System that is based on SQL for accessing Relational Databases.

• AKA: Natural Language Interface to Relational Databases.
• Context:
  • It was intially developed by Li & Jagadish (2014).
  • It consists of the following sub-systems:
    • an User Interface System,
    • a Depency Parser,
    • a Parse Tree Node Mapper,
    • a Parse Tree Structure Adjuster,
    • a Query Tree Translator,
    • an Intertive Communicator,
    • a RDBMS.
  • …
• Counter-Example(s):
  • AlLaDIn,
  • ENGLISH WIZARD,
  • INTELLECT,
  • LANGUAGEACCESS,
  • LOQUI.
  • PARLANCE,
  • PRECISE,
  • NaLIX,
  • NATURAL LANGUAGE,
  • Symantec Q&A.
• See: User Interface, Natural Language Processing, Natural Language Understanding, Natural Language Generation, Question Answering Task, NLQ, SQL.

---

---

References

2014

• (Li & Jagadish, 2014) ⇒ Fei Li, and H. V. Jagadish. (2014). “Constructing An Interactive Natural Language Interface for Relational Databases.” In: Proceedings of the VLDB Endowment Journal, 8(1). doi:10.14778/2735461.2735468
  • QUOTE: (...) we propose an NLIDB comprising three main components: a first component that transforms a natural language query to a query tree, a second component that verifies the transformation interactively with the user, and a third component that translates the query tree into a SQL statement. We have constructed such an NLIDB, and we call it a NaLIR (Natural Language Interface to Relational databases) (...)

     

    
    Figure 2: System Architecture

    Figure 2 depicts the architecture of NaLIR. The entire system we have implemented consists of three main parts: the query interpretation part, interactive communicator and query tree translator. The query interpretation part, which includes parse tree node mapper (Section 4) and structure adjustor (Section 5), is responsible for interpreting the natural language query and representing the interpretation as a query tree. The interactive communicator is responsible for communicating with the user to ensure that the interpretation process is correct. The query tree, possibly verified by the user, will be translated into a SQL statement in the query tree translator (Section 6) and then evaluated against an RDBMS.

---