This paper describes our system submission to the SemEval 2016 English Semantic Textual Similarity (STS) shared task. The proposed system is based on the compositional text similarity model, which aggregates pairwise word similarities for computing the semantic similarity between texts. In addition, our system combines word importance and word similarity to build an importance-similarity matrix...

Motivated by evidence in psycholinguistics and cognition, we propose a hierarchical distributed semantic model (DSM) that consists of low-dimensional manifolds built on semantic neighborhoods. Each semantic neighborhood is sparsely encoded and mapped into a low-dimensional space. Global operations are decomposed into local operations in multiple sub-spaces; results from these local operations a...

Usage-based theories of syntax predict that words and syntactic constructions are probabilistically interconnected. If this is true, then words that occur in similar distributions of syntactic constructions should prime each other. These effects should be fine-grained; even small differences between the syntactic distributions of pairs of words of the same grammatical category should cause vari...

We examine how people judge the probabilities of real-world events, such as natural disasters in different countries. We find that the associations between the words and phrases that constitute these events, as assessed by vector space semantic models, strongly correlate with the probabilities assigned to these events by participants. Thus, for example, the semantic proximity of “earthquake” an...

This paper presents a new semantic relatedness measure on semantic networks (SN) that uses both hierarchical and non-hierarchical relations. Our approach relies on two assumptions. Firstly, in a given SN, only a few numbers of paths can be considered as “semantically correct” and these paths obey to a given set of rules. Secondly, following a given edge in a path has a cost (which depends on it...

The contents and structure of semantic networks have been the focus of much recent research, with major advances in the development of distributional models. In parallel, connectionist modeling has extended our knowledge of the processes engaged in semantic activation. However, these two lines of investigation have rarely brought together. Here, starting from a standard textual model of semanti...

Approaches for measuring semantic similarity between words have been widely employed in various areas such as Artificial Intelligence, Linguistics, Cognitive Science and Knowledge Engineering. A new semantic similarity measure is proposed in this paper, which exploits the knowledge retrieved from a semantic network (i.e., WordNet) and the Internet. In particular, the structure information from ...

A framework for modeling Semantic Web Service is proposed. It is based on Description Logic (DL), hence it is endowed with a formal semantics and, in addition, it allows for expressing constraints in service descriptions of different strengths, i.e. Hard and Soft Constraints. Semantic service discovery can be performed by matching DL descriptions, expressing both Hard and Soft constraints, and ...

The purpose of this paper is to present a mathematical model for estimating semantic similarity among sentences in texts. The similarity measure is constructed from the semantic similarity among concepts and a set of concepts. Based on this model, we develop algorithms to calculate the semantic similarity between two set of concepts and then the ones to estimate the semantic similarity between ...