This work suggests a fine-grained mining of different types of contentious documents, towards a summarization of contention issues. We propose a Joint Topic Viewpoint model (JTV) for the unsupervised identification and the clustering of arguing expressions according to the latent topics they discuss and the implicit viewpoints they voice. A set of experiments is conducted on three type of conte...

Facial expressions are one of the parameters for accessing individual behavioral processes. Their recognition and verification can be framed as the identification of states of dynamical systems generated by physiological processes. Whereas a snap shot of a dynamical system gives information about its current state, a time series of past states captures its trajectory in state space. The descrip...

We investigate how neural networks can be used for hierarchical, compositional semantics. To this end, we define the simple but nontrivial artificial task of processing nested arithmetic expressions and study whether different types of neural networks can learn to add and subtract. We find that recursive neural networks can implement a generalising solution, and we visualise the intermediate st...

OBJECTIVE This study was designed to investigate whether increased urothelial cell apoptosis and chronic inflammation might contribute to recurrent urinary tract infection (UTI) in women. METHODS The bladder biopsy specimens were collected from thirty women with recurrent UTI and ten controls. The bladder biopsies were performed at one to two months after UTI episode had been completely resol...

Opinion expressions extraction is one of the main frameworks in opinion mining. Extracting negative opinions is more difficult than positive opinions because of indirect expressions. Especially, in the domain of consumer reviews, consumers are easier to be influenced by negative reviews when making decision. In this paper, we focus on the extraction of negative opinion expressions of consumer r...

A new direction in improving modern dialogue systems is to make a human-machine dialogue more similar to a human-human dialogue. This can be done by adding more input modalities. One additional modality for automatic dialogue systems is the facial expression of the human user. A common problem in a human-machine dialogue where the angry face may give a clue is the recurrent misunderstanding of ...

Talking heads and virtual characters, able to communicate complex information with human-like expressiveness and naturalness, should be able to display emotional facial expressions. In recent years several works, both rule-based and statistical, have obtained important results in the modelling of emotional facial expressions to be used in synthetic Talking Heads. However, most of the rule-based...

This paper is the basis paper for the accepted IJCNN challenge One-Minute Gradual-Emotion Recognition (OMG-Emotion) 1 by which we hope to foster long-emotion classification using neural models for the benefit of the IJCNN community. The proposed corpus has as novelty the data collection and annotation strategy based on emotion expressions which evolve over time into a specific context. Differen...

In this work, we study how to extend the capability of BLSTM networks to process data which are not only text strings but graphical two-dimensional languages such as handwritten mathematical expressions. The proposed solution aims at transforming the mathematical expression description into a sequence including at the same time symbol labels and relationship labels, so that classical supervised...

Visually impaired people, face many problems to communicate and to study electronical scientific documents especially those containing mathematics expressions. To provide solutions in this topic, we propose an assistive system to help blind people to categorize mathematical formulas from electronical documents. The system acts on four steps: first the translation of query math formula into Pres...