This paper describes the system used by the LIPN team in the Semantic Textual Similarity task at SemEval 2013. It uses a support vector regression model, combining different text similarity measures that constitute the features. These measures include simple distances like Levenshtein edit distance, cosine, Named Entities overlap and more complex distances like Explicit Semantic Analysis, WordN...

Abstract Our study proposes the use of a free classification task for investigating dimensions used by listeners in their perception nonnative sounds and predicting perceptual discriminability contrasts. In task, participants freely group auditory stimuli based on perceived similarity. The results can be to predict compared various acoustic or phonological determine relevant cues listeners. via...

This paper describes our submission for the *SEM shared task of Semantic Textual Similarity. We estimate the semantic similarity between two sentences using regression models with features: 1) n-gram hit rates (lexical matches) between sentences, 2) lexical semantic similarity between non-matching words, 3) string similarity metrics, 4) affective content similarity and 5) sentence length. Domai...

Multi-task learning aims at transferring knowledge between similar tasks. The multi-task Gaussian process framework of Bonilla et al. models (incomplete) responses of C data points for R tasks (e.g., the responses are given by an R×C matrix) by using a Gaussian process; the covariance function takes its form as the product of a covariance function defined on input-specific features and an inter...

In the present study, the specificity of repetition priming between semantic classification tasks was examined using Osgood's (Osgood, Suci, & Tannenbaum, 1957) semantic space as a heuristic for determining the similarity between classifications. The classification tasks involved judging the meaning of words on semantic scales, such as pleasant/unpleasant. The amount of priming across classific...

In Semantic Textual Similarity, systems rate the degree of semantic equivalence between two text snippets. This year, the participants were challenged with new data sets for English, as well as the introduction of Spanish, as a new language in which to assess semantic similarity. For the English subtask, we exposed the systems to a diversity of testing scenarios, by preparing additional OntoNot...

It is sometimes argued that the implementation of an overall similarity classification is less effortful than the implementation of a single-dimension classification. In the current article, we argue that the evidence securely in support of this view is limited, and report additional evidence in support of the opposite proposition--overall similarity classification is more effortful than single...

An autonomous agent using manmade objects must understand how task conditions the grasp placement. In this paper we formulate task based robotic grasping as a feature learning problem. Using a human demonstrator to provide examples of grasps associated with a specific task, we learn a representation, such that similarity in task is reflected by similarity in feature. The learned representation ...