In this contribution, we propose a method that uses a multilingual framework to validate the relevance of the notion of vector based semantic similarity between texts. The goal is to verify that vector based semantic similarities can be reliably transfered from one language to another. More precisely, the idea is to test whether the relative positions of documents in a vector space associated w...

The concept of semantic similarity is an important element in many applications such as information extraction, information retrieval, document clustering and ontology learning. Most of the previous works regarding semantic similarity measures have been traditionally defined between words or concepts (i.e. word-to-word similarity), thus ignoring the text or sentence that the concepts participat...

The aim of the present paper is to investigate the encoding and decoding of informativeness of verbs in German. Pairs of target verbs and nouns were either semantically unrelated (i.e. new) or related to each other in different ways. In a production study using read speech, these differences in semantic relatedness were found to be expressed in the prosodic realisation of the target words, nucl...

Semantic networks have been used extensively in psychology to describe how humans organize facts and knowledge in memory. Numerous methods have been proposed to construct semantic networks using data from memory retrieval tasks, such as the semantic fluency task (listing items in a category). However these methods typically generate group-level networks, and sometimes require a very large amoun...

One major deficiency of most semantic representation techniques is that they usually model a word type as a single point in the semantic space, hence conflating all the meanings that the word can have. Addressing this issue by learning distinct representations for individual meanings of words has been the subject of several research studies in the past few years. However, the generated sense re...

Knowledge transfer between object classes has been identified as an important tool for scalable recognition. However, determining which knowledge to transfer where remains a key challenge. While most approaches employ varying levels of human supervision, we follow the idea of mining linguistic knowledge bases to automatically infer transferable knowledge. In contrast to previous work, we explic...

The effect of exposure to an original or common idea on crowdsourced idea generation was studied by asking crowd workers to design a public service advertisement. As compared to having no idea exposure, exposure to an original idea decreased fluency and increased the average originality of ideas generated by each person. By contrast, exposure to a common idea had no effect on either idea origin...

Given two sentences, participating systems assign a semantic similarity score in the range of 0-5. We applied two different techniques for the task: one is based on lexical semantic net (corresponding to run 1) and the other is based on deep learning semantic model (corresponding to run 2). We also combined these two runs linearly (corresponding to run 3). Our results indicate that the two tech...

Evaluation methods for Distributional Semantic Models typically rely on behaviorally derived gold standards. These methods are difficult to deploy in languages with scarce linguistic/behavioral resources. We introduce a corpus-based measure that evaluates the stability of the lexical semantic similarity space using a pseudo-synonym same-different detection task and no external resources. We sho...

Semantic similarity is central for the functioning of semantically enabled processing of geospatial data. It is used to measure the degree of potential semantic interoperability between data or different geographic information systems (GIS). Similarity is essential for dealing with vague data queries, vague concepts or natural language and is the basis for semantic information retrieval and int...