The performance of content-based image retrieval using low-level visual content has largely been judged to be unsatisfactory. Perceived performance could probably be improved if retrieval were based on higher-level content. However, researchers have not been very successful in bridging what is now called the "semantic gap" between low-level content detectors and higher-level visual content. Thi...

We present a method for determining the context-dependent denotation of simple object-denoting mathematical expressions in mathematical documents. Our approach relies on estimating the similarity between the linguistic context within which the given expression occurs and a set of terms from a flat domain taxonomy of mathematical concepts; one of 7 head concepts dominating a set of terms with hi...

This paper reports the STS-UHH participation in the SemEval 2017 shared Task 1 of Semantic Textual Similarity (STS). Overall, we submitted 3 runs covering monolingual and cross-lingual STS tracks. Our participation involves two approaches: unsupervised approach, which estimates a word alignment-based similarity score, and supervised approach, which combines dependency graph similarity and cover...

The effect of phonological similarity on L1–L2 cognate translation priming was examined with Japanese– English bilinguals. According to the phonological account, the cognate priming effect for different-script bilinguals consists of additive effects of phonological and conceptual facilitation. If true, then the size of the cognate priming effect would be directly influenced by the phonological ...

Motivated by cognitive lexical models, network-based distributional semantic models (DSMs) were proposed in [Iosif and Potamianos (2013)] and were shown to achieve state-of-the-art performance on semantic similarity tasks. Based on evidence for cognitive organization of concepts based on degree of concreteness, we investigate the performance and organization of network DSMs for abstract vs. con...

This article describes a method used to calculate the similarity between short English texts, specifically of sentence length. The described algorithm calculates semantic and word order similarities of two sentences. In order to do so, it uses a structured lexical knowledge base and statistical information from a corpus. The described method works well in determining sentence similarity for mos...

We consider the problem of tracking information over time and across sources in clusters of news stories about emergency events. While previous approaches have focused on finding new information at the document and sentence levels (e.g. TDT FSD and the TREC Novelty track, respectively), we are interested in following information at the factual level. Specifically, we propose to develop a “fact ...

This paper presents a stochastic graph based method for recommending or selecting a small subset of blogs that best represents a much larger set. within a certain topic. Each blog is assigned a score that reflects how representative it is. Blog scores are calculated recursively in terms of the scores of their neighbors in a lexical similarity graph. A random walk is performed on a graph where n...