Open AccessNatural Language Access to Enterprise Data
Author(s) -
Waltinger Ulli,
Tecuci Dan,
Olteanu Mihaela,
Mocanu Vlad,
Sullivan Sean
Publication year - 2014
Publication title -
ai magazine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.597
H-Index - 79
eISSN - 2371-9621
pISSN - 0738-4602
DOI - 10.1609/aimag.v35i1.2502
Subject(s) - computer science , syntax , data control language , semantics (computer science) , natural language , set (abstract data type) , data access , enterprise data management , question answering , interpretation (philosophy) , query language , data manipulation language , programming language , information retrieval , enterprise information system , database , world wide web , data science , artificial intelligence , web search query , query by example , search engine
This article describes USI Answers — a natural language question‐answering system for enterprise data. We report on the progress toward the goal of offering easy access to enterprise data to a large number of business users, most of whom are not familiar with the specific syntax or semantics of the underlying data sources. Additional complications come from the nature of the data, which comes both as structured and unstructured. The proposed solution allows users to express questions in natural language, makes apparent the system's interpretation of the query, and allows easy query adjustment and reformulation. The application is in use by more than 1500 users from Siemens Energy. We evaluate our approach on a data set consisting of feet data.