A compiler-compiler for visual languages is presented. It has been designed as a framework for building visual programming environments that translate schemas into textual representation as well as into programs representing the deep meaning of schemas. The deep semantics is implemented by applying attribute grammars to schema languages; attribute dependencies are implemented as methods of Java...

This paper compares language modeling techniques for dialog act segmentation of multiparty meetings. The evaluation is twofold; we search for a convenient representation of textual information and an efficient modeling approach. The textual features capture word identities, parts-of-speech, and automatically induced classes. The models under examination include hidden event language models, max...

This paper deals with a new feature selection and feature contrasting approach for classification of highly unbalanced textual data with a high degree of similarity between associated classes. The efficiency of the approach is illustrated by its capacity to enhance the classification of bibliographic references into a patent classification scheme. A complementary experiment is performed on a no...

Existing parsers for textual model representation formats such as XMI and HUTN are unforgiving and fail upon even the smallest inconsistency between the structure and naming of metamodel elements and the contents of serialised models. In this paper, we demonstrate how a flexible parsing approach can transparently and automatically resolve a number of these inconsistencies, and how it can eventu...

This paper describes a novel undertaking: comparing the relationship between grammatical ambiguity (syncretism) in nouns, as represented in a default inheritance hierarchy, with textual frequency distributions. In order to do this we consider a language with a reasonable number of grammatical distinctions and where syncretism occurs in different morphological classes. We investigated this relat...

This paper proposes a new model for extracting an interpretable sentence embedding by introducing self-attention. Instead of using a vector, we use a 2-D matrix to represent the embedding, with each row of the matrix attending on a different part of the sentence. We also propose a self-attention mechanism and a special regularization term for the model. As a side effect, the embedding comes wit...

We introduce a low-complexity method for acquiring fine-grained classes of named entities from the Web. The method exploits the large amounts of textual data available on the Web, while avoiding the use of any expensive text processing techniques or tools. The quality of the extracted classes is encouraging with respect to both the precision of the sets of named entities acquired within various...

Methods and results Geneva prison (for men and women) has 300 beds and serves as a remand prison and for short and medium term sentences. One fifth of the prisoners are dependent on opiates at entry. For our study we cross checked prison medical records with medicolegal necropsv reports in the Canton of Geneva. During 1982-6, 102 sudden deaths among former prisoners were recorded, of which a la...