Edward L. Wimmers

A framework for expressing and combining preferences

The advent of the World Wide Web has created an explosion in the available on-line information. As the range of potential choices expand, the time and effort required to sort through them also expands. We propose a formal framework for expressing and combining user preferences to address this problem. Preferences can be used to focus search queries and to order the search results. A preference is expressed by the user for an entity which is described by a set of named fields; each field can take on values from a certain type. The * symbol may be used to match any element of that type. A set of preferences can be combined using a generic combine operator which is instantiated with a value function, thus providing a great deal of flexibility. Same preferences can be combined in more than one way and a combination of preferences yields another preference thus providing the closure property. We demonstrate the power of our framework by illustrating how a currently popular personalization system and a real-life application can be realized as special cases of our framework. We also discuss implementation of the framework in a relational setting.

Type inclusion constraints and type inference

We present a general algorithm for solving systems of inclusion constraints over type expressions. The constraint language includes function types, constructor types, and liberal intersection and union types. We illustrate the application of our constraint solving algorithm with a type inference system for the lambda calculus with constants. In this system, every pure lambda term has a (computable) type and every term typable in the Hindley/Milner system has all of its Hindley/Milner types. Thus, the inference system is an extension of the Hindley/Milner system that can type a very large set of lambda terms.

Soft typing with conditional types

We present a simple and powerful type inference method for dynamically typed languages where no type information is supplied by the user. Type inference is reduced to the problem of solvability of a system of type inclusion constraints over a type language that includes function types, constructor types, union, intersection, and recursive types, and conditional types. Conditional types enable us to analyze control flow using type inference, thus facilitating computation of accurate types. We demonstrate the power and practicality of the method with examples and performance results from an implementation.

Solving systems of set constraints

It is shown that systems of set constraints that use all the standard set operations, especially unrestricted union and complement, can be solved. The centerpiece of the development is an algorithm that incrementally transforms a system of constraints while preserving the set of solutions. Eventually, either the system is shown to be inconsistent or all solutions can be exhibited. Most of the work is in proving that if this algorithm does not discover an inconsistency, then the system has a solution. This is done by showing that the system of constraints generated by the algorithm can be transformed into an equivalent set of equations that are guaranteed to have a solution. These equations are essentially tree automata.<<ETX>>

The Complexity of Set Constraints

Set constraints are relations between sets of terms. They have been used extensively in various applications in program analysis and type inference. We present several results on the computational complexity of solving systems of set constraints. The systems we study form a natural complexity hierarchy depending on the form of the constraint language.

A formula for incorporating weights into scoring rules

Abstract A “scoring rule” is an assignment of a value to every tuple (of varying sizes). This paper is concerned with the issue of how to modify a scoring rule to apply to the case where weights are assigned to the importance of each argument. We give an explicit formula for incorporating weights that can be applied no matter what the underlying scoring rule is. The formula is surprisingly simple, in that it involves far fewer terms than one might have guessed. It has three further desirable properties. The first desirable property is that when all of the weights are equal, then the result is obtained by simply using the underlying scoring rule. Intuitively, this says that when all of the weights are equal, then this is the same as considering the unweighted case. The second desirable property is that if a particular argument has zero weight, then that argument can be dropped without affecting the value of the result. The third desirable property is that the value of the result is a continuous function of the weights. We show that if these three desirable properties hold, then under one additional assumption (a type of local linearity), our formula gives the unique possible answer.

Querying multimedia data from multiple repositories by content: the Garlic project

We describe Garlic, an object-oriented multimedia middleware query system. Garlic enables existing data management components, such as a relational database or a full text search engine, to be integrated into an extensible information management system that presents a common interface and user access tools. We focus in this paper on how QBIC, an image retrieval system that provides content-based image queries, can be integrated into Garlic. This results in a system in which a single query can combine visual and nonvisual data using type-specific search techniques, enabling a new breed of multimedia applications

Incorporating User Preferences in Multimedia Queries

In a multimedia database system, queries may be fuzzy: thus, the answer to a query such as (Color=‘red’) may not be 0 (false) or 1 (true), but instead a number between 0 and 1. A conjunction, such as (Color=‘red’) ∧ (Sound=‘loud’), is evaluated by first evaluating the individual conjuncts and then combining the answers by some scoring function. Typical scoring functions include the min (the standard scoring function for the conjunction in fuzzy logic) and the average. We address the question of how to permit the user to weight the importance of atomic subformulas. In particular, we give a semantics for permitting non-uniform weights, by giving an explicit formula (that is based on the underlying scoring function). This semantics permits an efficient implementation with a low database access cost in a multimedia database system in important cases of interest.

Decidability of Systems of Set Constraints with Negative Constraints

Set constraints are relations between sets of terms. They have been used extensively in various applications in program analysis and type inference. Recently, several algorithms for solving general systems of positive set constraints have appeared. In this paper we consider systems of mixed positive and negative constraints, which are considerably more expressive than positive constraints alone. We show that it is decidable whether a given such system has a solution. The proof involves a reduction to a number-theoretic decision problem that may be of independent interest.

Using Fagin's algorithm for merging ranked results in multimedia middleware

A distributed multimedia information system allows users to access data of different modalities, from different data sources, ranked by various combinations of criteria. Fagin (1996) gives an algorithm for efficiently merging multiple ordered streams of ranked results, to form a new stream ordered by a combination of those ranks. In this paper we describe the implementation of Fagins algorithm in an actual multimedia middleware system, including a novel, incremental version of the algorithm that supports dynamic exploration of data. We show that the algorithm would perform well as part of a single multimedia server and can even be effective in the distributed environment (for a limited set of queries), but that the assumptions it makes about random access limit its applicability dramatically. Our experience provides a better understanding of an important algorithm, and exposes an open problem for distributed multimedia information systems.