This paper describes our participation in the Recognizing Textual Entailment challenge (RTE-5) in the Text Analysis Conference (TAC 2009). Following the two-stage binary classification strategy, our focus this year is to recognize related Text-Hypothesis pairs instead of entailment pairs. In particular, we propose a joint syntactic-semantic representation to better capture the key information s...

In this paper we present a model transformation from a visual representation (VisualOCL) of the Object Constraint Language (OCL) to the textual one using graph transformation. Starting from VisualOCL diagrams, we show how their underlying abstract syntax can be modeled by typed attributed graphs and converted into an OCL string representation using graph transformation rules.

Animation scripts are an integral part of developing computer games: they describe which character animations to play and when to switch between animations. These scripts are often written in text editors which can be an error-prone task since there are multiple variables and conditions that needs to be understood, and text editors gives no indication of how animations are linked together. This...

The objective of knowledge graph embedding is to encode both entities and relations of knowledge graphs into continuous low-dimensional vector spaces. Previously, most works focused on symbolic representation of knowledge graph with structure information, which can not handle new entities or entities with few facts well. In this paper, we propose a novel deep architecture to utilize both struct...

y Abstract. A structured operational semantics is presented for Timed and Hybrid Statecharts, which are generalizations of the visual speciication language of Statecharts intended to model real-time and hybrid systems. In order to study some of the basic features of Statecharts and the extensions necessary to treat real-time and continuous behaviors without being distracted by the graphical rep...

In text stream analysis one of the main problems is finding an effective method to classify documents fast and correctly. This is the reason why dimensionality reduction and related methods of representation of significant information are critical to develop a good text classifier. In this report we describe a novel purely combinatorial approach to obtain a meaningful representation of text dat...

This paper presents the graphical representation of textual data using text categorization; we had concentrated on the compact representation of the document. Text Categorization has become an important task in data mining (text mining) because of the development of electronic commerce over the internet. All organizations that have business based on internet need an effective categorization met...

In this paper we deal with the problem of addition of new documents in collection when documents are represented in lower dimensional space by concept indexing. Concept indexing (CI) is a method of feature construction that is relying on concept decomposition of term-document matrix. By using CI original representations of documents are projected on the space spread by centroids of clusters, wh...

This paper provides a first investigation over existing textual inference paradigms in order to propose a generic framework able to capture major semantic aspects in Human Robot Interaction (HRI). We investigate the use of general semantic paradigms used in Natural Language Understanding (NLU) tasks, such as Semantic Role Labeling, over typical robot commands. The semantic information obtained ...

Automatic classification of news articles is a relevant problem due to the large amount of news generated every day, so it is crucial that these news are classified to allow for users to access to information of interest quickly and effectively. Traditional classification systems represent documents as bag-of-words (BoW), which are oblivious to two problems of language: synonymy and polysemy. T...