NaLIX
Jump to navigation
Jump to search
A NaLIX is a Natural Language Database Interface System for accessing XML Databases using XQuery Language.
- AKA: Natural Language Interface to XML.
- Context:
- It was intially developed by Li et al. (2005).
- It consists of two main subsystems:
- …
- Counter-Example(s):
- See: User Interface, Natural Language Processing, Natural Language Understanding, Natural Language Generation, Question Answering Task, SQL, Parse Tree.
References
2005
- (Li et al., 2005) ⇒ Yunyao Li, Huahai Yang, and H. V. Jagadish. (2005). “NaLIX: An Interactive Natural Language Interface for Querying XML.” In: Proceedings of the 2005 ACM SIGMOD International Conference on Management of data. ISBN:1-59593-060-4 doi:10.1145/1066157.1066281
- QUOTE: We describe NaLIX (Natural Language Interface to XML), a generic interactive natural language interface to XML database systems. Our focus is on the second challenge: given a parsed natural language query, how to translate it into a correctly structured query against the database. In NaLIX, an arbitrary English language sentence, which can be quite complex and include aggregation, nesting, and value joins, among other things, is translated, potentially after reformulation, into an XQuery expression that can be evaliated against an XML database. For example, it is possible for the user to write “find the title of publications with more than 5 authors” without having to worry about the actual structural relationships among the elements/attributes or the actual element/attribute names used in the XML documents for title, publication, or author. In addition, automatic semantic grouping based on the user query will be performed to determine query nesting and grouping (...)
Figure 1 depicts the architecture of NaLIX. The entire NaLIX system consists of two parts: one part is responsible for query translation from natural langauge queries to XQuery, including parse tree classifier, validator and translator ; the other provides supports for interactive query formulation, including query repository and message generator. A typical user interaction process in NaLIX involves both query translation and interactive query formulation.
Figure 1: Architecture of NaLIX
- QUOTE: We describe NaLIX (Natural Language Interface to XML), a generic interactive natural language interface to XML database systems. Our focus is on the second challenge: given a parsed natural language query, how to translate it into a correctly structured query against the database. In NaLIX, an arbitrary English language sentence, which can be quite complex and include aggregation, nesting, and value joins, among other things, is translated, potentially after reformulation, into an XQuery expression that can be evaliated against an XML database. For example, it is possible for the user to write “find the title of publications with more than 5 authors” without having to worry about the actual structural relationships among the elements/attributes or the actual element/attribute names used in the XML documents for title, publication, or author. In addition, automatic semantic grouping based on the user query will be performed to determine query nesting and grouping (...)
