Ad-hoc queries are usually short, of perhaps two to ten terms. However, in previous rounds of TREC we have concentrated on obtaining optimal performance for the long TREC topics. In this paper we investigate the behaviour of similarity measures on short queries, and show experimentally that two successful measures|which give similar, good performance on long TREC topics|do not work well for sho...

This paper reports the results of two experiments aimed at assessing the perceived similarity between a set of English and Catalan vowels from the perspective of native speakers of both languages. Two groups of 27 listeners, a group of native English speakers and a group of native Catalan speakers, used a 9-point scale to rate the degree of similarity between two stimuli. Crucial stimuli consis...

JAYASHREE SUBRAHMONIA IBM T.J. Watson Research, P.O. Box 218 / Route 134, Yorktown Heights, NY 10598, U. S. A. E-mail: [email protected] This paper addresses the problem of improving the performance of an online, writer-independent, large-vocabulary, unconstrained, handwriting recognition system by clustering writers with similar writing styles. Recognition performance is enhanced by identify...

Analyses of similarities and changes in protein conformation can provide important information regarding protein function and evolution. Many scores, including the commonly used root mean square deviation, have therefore been developed to quantify the similarities of different protein conformations. However, instead of examining individual conformations it is in many cases more relevant to anal...

Similarity assessment plays a key role in lazy learning methods such as knearest neighbor or case-based reasoning. In this paper we will show how refinement graphs, that were originally introduced for inductive learning, can be employed to assess and reason about similarity. We will define and analyze two similarity measures, $S_{?}$ and $S_{?}$, based on refinement graphs. The \emph{anti-unifi...

We develop a new method to rank the degree of similarity between Boolean expressions contrast it with other known methods and describe its implementation Our method reduces time and space complexity from exponential to polynomial in the number of Boolean terms Index Terms Boolean query information retrieval ranking resource discovery similarity measure

Many machine learning and data mining algorithms on the similarity metrics. The Cosine similarity, wh the inner product of two normalized feature vectors, most commonly used similarity measures. Howev practical tasks such as text categorization an clustering, the Cosine similarity is calculated assumption that the input space is an orthogonal usually could not be satisfied due to synonymy an Va...

We enrich sets with an integrated notion of similarity, measured in a (complete) lattice, special cases of which are reflexive sets and bounded metric spaces. Relations and basic relational operations of traditional relational algebra are interpreted in such richer structured environments. An canonical similarity measure between relations is introduced. In the special case of reflexive sets it ...

Algorithms for learning distributions over weight-vectors, such as AROW (Crammer et al., 2009) were recently shown empirically to achieve state-of-the-art performance at various problems, with strong theoretical guaranties. Extending these algorithms to matrix models pose challenges since the number of free parameters in the covariance of the distribution scales as n with the dimension n of the...