RAF: An Activation Framework for Refining Similarity Queries Using Learning Techniques

Ma, Yiming; Mehrotra, Sharad; Seid, Dawit Yimam; Qi, Zhong

doi:10.1007/11733836_41

Cited by 7 publications

(13 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yet, before [12], [5], [11], [27] and [10], Motro [23], [24] has discussed the query modification techniques for supporting vague queries and the approaches for explaining empty answer to a query, respectively. In user feedback-based query refinement techniques, only false positives (why) feedback have been emphasized in both database and information extraction areas previously [20], [19]. For example, in [20], Ma et al model user feedback query refinement for both learning the structure of the query as well as learning the relative importance of query components, but they collect only false positive feedback from users.…”

Section: Related Workmentioning

confidence: 97%

“…In user feedback-based query refinement techniques, only false positives (why) feedback have been emphasized in both database and information extraction areas previously [20], [19]. For example, in [20], Ma et al model user feedback query refinement for both learning the structure of the query as well as learning the relative importance of query components, but they collect only false positive feedback from users. In [19], Liu et al collect false positives (why tuples), again identified by users, to modify the initial rules in information extraction settings.…”

Section: Related Workmentioning

confidence: 97%

See 1 more Smart Citation

On answering why and why-not questions in databases

Islam

2013

2013 IEEE 29th International Conference on Data Engineering Workshops (ICDEW)

View full text Add to dashboard Cite

There is a growing interest in allowing users to ask questions on received results in the hope of improving the usability of database systems. This research aims at answering the so called why and why-not questions on received results w.r.t. different query settings in databases. The main goals of this research are: (i) studying the problem of answering the why and the why-not questions in databases; (ii) finding efficient strategies for answering these questions in terms of different query settings and (iii) finally, developing a framework that can take advantage of the existing data indexing and query evaluation techniques available to answer such questions in databases. We believe that the research undertaken by us can contribute towards improving the usability of traditional database systems. I. INTRODUCTIONAfter decades of efforts made by the database community, today's systems have become highly efficient in terms of both query execution time and resource usage. However, these systems are not usable for the end users to the same degree as they are proficient in underlying data management and query evaluation [16]. These days users expect systems to be more interactive and cooperative. That is, the users are not satisfied only with receiving the result from the system, but also they want to know why the system returns only the current set of objects in the result set (i.e., the current result set does not match the user's expectation). In particular, users may want to know why a certain data object (which is unexpected) appears in the result set and similarly, why a certain data object (which is expected) does not appear in the result set. As a next step, users may also seek appropriate explanations for these questions. Any system that can provide good explanations for the above questions can be very helpful for users to understand their information needs and also make the system more interactive and transparent to the users [27], [10], [13]. At present, our traditional database systems do not provide any kind of exploratory data analysis facilities to support the above why and why not questions.There are different aspects of answering why and why-not questions in databases. These are: (i) computing provenance (also called "lineage" or "pedigree") information to describe the origins of data output and the process by which it was arrived at [4], [6] ; (ii) modifying the original database so that missing objects become part of the query output [12], [11] ; (iii) identifying the causes (e.g., operator(s) in the user submitted query) that filters the desired query output [5]; and (iv) modifying the query so that missing objects appear in

show abstract

Section: Related Workmentioning

confidence: 97%

Section: Related Workmentioning

confidence: 97%

On answering why and why-not questions in databases

Islam

2013

2013 IEEE 29th International Conference on Data Engineering Workshops (ICDEW)

View full text Add to dashboard Cite

show abstract

“…In user feedback-based query refinement techniques, only false positives (why) feedback have been emphasized in both database and information extraction areas before [14], [15]. In [14], Ma et al model user feedback query refinement for both learning the structure of the query as well as learning the relative importance of query components, but they collect VII.…”

Section: A Effectivenessmentioning

confidence: 98%

“…In [14], Ma et al model user feedback query refinement for both learning the structure of the query as well as learning the relative importance of query components, but they collect VII. RELATED WORK AND DISCUSSION Previous studies [5], [4], [6], [2] and [3] have addressed …”

Section: A Effectivenessmentioning

confidence: 99%

On answering why-not questions in reverse skyline queries

Islam

Zhou

Liu

2013

2013 IEEE 29th International Conference on Data Engineering (ICDE)

View full text Add to dashboard Cite

This paper aims at answering the so called whynot questions in reverse skyline queries. A reverse skyline query retrieves all data points whose dynamic skylines contain the query point. We outline the benefit and the semantics of answering why-not questions in reverse skyline queries. In connection with this, we show how to modify the why-not point and the query point to include the why-not point in the reverse skyline of the query point. We then show, how a query point can be positioned safely anywhere within a region (i.e., called safe region) without losing any of the existing reverse skyline points. We also show how to answer why-not questions considering the safe region of the query point. Our approach efficiently combines both query point and data point modification techniques to produce meaningful answers. Experimental results also demonstrate that our approach can produce high quality explanations for why-not questions in reverse skyline queries.

show abstract

“…Our work significantly differs from these retrieval and refinement approaches (e.g., [4,7]) since we focus on the existing query formulation, and attempts to give a user a sense of the query completion as we dynamically prune the search space based on the user feedback. In addition, our refinement techniques are built on top of the dynamic search space.…”

Section: Related Workmentioning

confidence: 99%

Integrating Similarity Retrieval and Skyline Exploration Via Relevance Feedback

Mehrotra

2007

Advances in Databases: Concepts, Systems and Applications

Self Cite

View full text Add to dashboard Cite

Abstract. Similarity retrieval have been widely used in many practical search applications. A similarity query model can be viewed as a logical combination of a set of similarity predicates. A user can initialize a query model, but model parameters or the model itself may be inadequately specified. As a result, a retrieval system cannot guarantee that it has presented all the relevant tuples to the user. In this paper, we propose a framework that integrates the similarity retrieval and skyline exploration. Using the relevance feedback as a way to constrain the search space, our framework can intelligently explore only a necessary portion of data that contains all the relevant tuples. Our framework is also flexible enough to incorporate model refinement techniques to retrieving relevant results as early as possible.

show abstract

RAF: An Activation Framework for Refining Similarity Queries Using Learning Techniques

Cited by 7 publications

References 12 publications

On answering why and why-not questions in databases

On answering why and why-not questions in databases

On answering why-not questions in reverse skyline queries

Integrating Similarity Retrieval and Skyline Exploration Via Relevance Feedback

Contact Info

Product

Resources

About