This paper describes the work done by the JRS team for the linking sub-task. We submitted eight pairs of runs: four with different textual resources only, two using reranking based on visual similarity, and two using concept detection results. Each of the pairs contains of one run using the anchor segment only, and one using a longer context segment. The results show higher variance between anc...

In this work we provide an initial analysis of service categorization, the process of associating services with ontologies. Service categorization is an important pre-processing step to tasks such as service composition. The absence of semantic understanding of services may yield erroneous compositions and therefore, service categorization can assist in determining the correctness of a composit...

We report on an experiment where the decision behavior of annotators issuing linguistic metadata is observed with an eyetracking device. As experimental conditions we consider the role of textual context and linguistic complexity classes. Still preliminary in nature, our data suggests that semantic complexity is much harder to deal with than syntactic one, and that full-scale textual context is...

The expansion of structured information in different applications introduces a new ambiguity in multimedia retrieval in semi-structured documents. We investigate in this paper the combination of textual and structural context for multimedia retrieval in XML document thus we present a indexing model which combines textual and structural information. We propose a geometric method who use implicit...

This paper presents an experimental comparison of Interestingness Measures (IMs), in the context of an approach designed for matching textual taxonomies. This extensional and asymmetric approach makes use of association rule model for matching entities issued from two textual hierarchies. We select 6 IMs and we perform two experiments on a benchmark composed of two textual taxonomies and a set ...

Abstract: By presenting textual information within the space of corresponding images, the concept of DUAL-USE OF IMAGE SPACE (DUIS) eases the mental integration of textual and pictorial information. This paper applies the DUIS approach which was initially developed for area features to linear features. Moreover, we enhance the DUIS approach with new tools to navigate within embedded texts: The ...

In the work here presented, we apply textual and sequential methods to assess the outcomes of an unconstrained multiparty dialogue. In the context of chat transcripts from a collaborative learning scenario, we demonstrate that while low-level textual features can indeed predict student success, models derived from sequential discourse act labels are also predictive, both on their own and as a s...

Context based API recommendation is an important way to help developers find the needed APIs effectively and efficiently. For effective recommendation, we need not only a joint view of both structural textual code information, but also holistic correlated usage in control data flow graph as whole. Unfortunately, existing methods exploit or information separately. In this work, propose novel app...

A system is introduced that increases the information density of textual presentation by reconsidering text as pictures, expanding the range of written expression. Indicating nested associativity with stripes, Zebrackets uses small-scale horizontal striations, superimposed on parenthetical delimi t e r~ . This system is implemented as an active filter that re-presents textual information graphi...