Abstract. In Business Intelligence systems, users interact with data warehouses by formulating OLAP queries aimed at exploring multidimensional data cubes. Being able to predict the most likely next queries would provide a way to recommend interesting queries to users on the one hand, and could improve the efficiency of OLAP sessions on the other. In particular, query recommendation would proactively guide users in data exploration and improve the quality of their interactive experience. In this paper, we propose a framework to predict the most likely next query and recommend this to the user. Our framework relies on a probabilistic user behavior model built by analyzing previous OLAP sessions and exploiting a query similarity metric. To gain insight in the recommendation precision and on what parameters it depends, we evaluate our approach using different quality assessments.
Abstract. Business Intelligence (BI) aims at providing methods and tools that lead to quick decisions from trusted data. Such advanced tools require some technical knowledge on how to formulate the queries. We propose a natural language (NL) interface for a Data Warehouse based Question Answering system. This system allows users to query with questions expressed in natural language. The proposed system is fully automated, resulting low Total Cost of Ownership. We aim at demonstrating the importance of identifying already existing semantics and using Text Mining techniques on the Web to move toward the users's need.
Abstract-Question Answering (Q&A) from structured data is a technique that may revolutionize enterprise search. A very promising use-case for such technology is Business Intelligence (BI). In order to make BI more accessible to end-users, some efforts have been made in the field of search for existing reports. However, the problem of converting an end-user's natural language input to a valid structured query in an ad-hoc fashion hasn't been sufficiently solved yet. In this paper we present a framework for Q&A systems that operate on structured data. The main innovation is that the framework allows defining a mapping between recognized semantics of a user's questions to a structured query model that can be executed on arbitrary data sources. It bases on popular standards like RDF and SparQL and is therefore very easy to adapt to other domains or usecases. We will describe the application of this framework at hand of a BI question answering use-case, which also includes the personalization of generated queries, demonstrating the realworld applicability of our approach. In our experiments, we demonstrate that with our approach one can easily achieve a similar answering quality as one of the most popular Q&A systems on the Web.
Abstract. As the amount and complexity of data keeps increasing in data warehouses, their exploration for analytical purposes may be hindered. Recommender systems have grown very popular on the Web with sites like Amazon, Netflix, etc. These systems proved successful to help users explore available content related to what they are currently looking at. Recent systems consider the use of recommendation techniques to suggest data warehouse queries and help an analyst pursue its exploration. In this paper, we present a personalized query expansion component which suggests measures and dimensions to iteratively build consistent queries over a data warehouse. Our approach leverages (a) semantics defined in multi-dimensional domain models, (b) collaborative usage statistics derived from existing repositories of Business Intelligence documents like dashboards and reports and (c) preferences defined in a user profile. We finally present results obtained with a prototype implementation of an interactive query designer.
Abstract. Question Answering systems, unlike other Information Retrieval systems, aim at providing directly the answer to the user, and not a list of documents in which the correct answer may be found. Our system is based on Data Warehouses and provides composite answers made of data tables and corresponding chart visualizations for Business Intelligence purposes. The question translation step is based on a new proposal for surface patterns that incorporate business semantic as well as domain-specific knowledge allowing a better coverage of questions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.