Pierre Nugues

Virtual Reality Therapy Versus Cognitive Behavior Therapy for Social Phobia: A Preliminary Controlled Study

Social phobia is one of the most frequent mental disorders and is accessible to two forms of scientifically validated treatments: anti-depressant drugs and cognitive behavior therapies (CBT). In this last case, graded exposure to feared social situations is one of the fundamental therapeutic ingredients. Virtual reality technologies are an interesting alternative to the standard exposure in social phobia, especially since studies have shown its usefulness for the fear of public speaking. This paper reports a preliminary study in which a virtual reality therapy (VRT), based on exposure to virtual environments, was used to treat social phobia. The sample consisted of 36 participants diagnosed with social phobia assigned to either VRT or a group-CBT (control condition). The virtual environments used in the treatment recreate four situations dealing with social anxiety: performance, intimacy, scrutiny, and assertiveness. With the help of the therapist, the patient learns adapted cognitions and behaviors in order to reduce anxiety in the corresponding real situations. Both treatments lasted 12 weeks, and sessions were delivered according to a treatment manual. Results showed statistically and clinically significant improvement in both conditions. The effect-sizes comparing the efficacy of VRT to the control traditional group-CBT revealed that the differences between the two treatments are trivial.

Dependency-based Syntactic--Semantic Analysis with PropBank and NomBank

This paper presents our contribution in the closed track of the 2008 CoNLL Shared Task (Surdeanu et al., 2008). To tackle the problem of joint syntactic--semantic analysis, the system relies on a syntactic and a semantic subcomponent. The syntactic model is a bottom-up projective parser using pseudo-projective transformations, and the semantic model uses global inference mechanisms on top of a pipeline of classifiers. The complete syntactic--semantic output is selected from a candidate pool generated by the subsystems. The system achieved the top score in the closed challenge: a labeled syntactic accuracy of 89.32%, a labeled semantic F1 of 81.65, and a labeled macro F1 of 85.49.

Multilingual Semantic Role Labeling

This paper describes our contribution to the semantic role labeling task (SRL-only) of the CoNLL-2009 shared task in the closed challenge (Hajic et al., 2009). Our system consists of a pipeline of independent, local classifiers that identify the predicate sense, the arguments of the predicates, and the argument labels. Using these local models, we carried out a beam search to generate a pool of candidates. We then reranked the candidates using a joint learning approach that combines the local models and proposition features. To address the multilingual nature of the data, we implemented a feature selection procedure that systematically explored the feature space, yielding significant gains over a standard set of features. Our system achieved the second best semantic score overall with an average labeled semantic F1 of 80.31. It obtained the best F1 score on the Chinese and German data and the second best one on English.

Dependency-based Semantic Role Labeling of PropBank

We present a PropBank semantic role labeling system for English that is integrated with a dependency parser. To tackle the problem of joint syntactic--semantic analysis, the system relies on a syntactic and a semantic subcomponent. The syntactic model is a projective parser using pseudo-projective transformations, and the semantic model uses global inference mechanisms on top of a pipeline of classifiers. The complete syntactic-semantic output is selected from a candidate pool generated by the subsystems. We evaluate the system on the CoNLL-2005 test sets using segment-based and dependency-based metrics. Using the segment-based CoNLL-2005 metric, our system achieves a near state-of-the-art F1 figure of 77.97 on the WSJ+Brown test set, or 78.84 if punctuation is treated consistently. Using a dependency-based metric, the F1 figure of our system is 84.29 on the test set from CoNLL-2008. Our system is the first dependency-based semantic role labeler for PropBank that rivals constituent-based systems in terms of performance.

LTH: Semantic Structure Extraction using Nonprojective Dependency Trees

We describe our contribution to the SemEval task on Frame-Semantic Structure Extraction. Unlike most previous systems described in literature, ours is based on dependency syntax. We also describe a fully automatic method to add words to the FrameNet lexical database, which gives an improvement in the recall of frame detection.

The Effect of Syntactic Representation on Semantic Role Labeling

Almost all automatic semantic role labeling (SRL) systems rely on a preliminary parsing step that derives a syntactic structure from the sentence being analyzed. This makes the choice of syntactic representation an essential design decision. In this paper, we study the influence of syntactic representation on the performance of SRL systems. Specifically, we compare constituent-based and dependency-based representations for SRL of English in the FrameNet paradigm. Contrary to previous claims, our results demonstrate that the systems based on dependencies perform roughly as well as those based on constituents: For the argument classification task, dependency-based systems perform slightly higher on average, while the opposite holds for the argument identification task. This is remarkable because dependency parsers are still in their infancy while constituent parsing is more mature. Furthermore, the results show that dependency-based semantic role classifiers rely less on lexicalized features, which makes them more robust to domain changes and makes them learn more efficiently with respect to the amount of training data.

Generating a 3D simulation of a car accident from a written description in natural language: the CarSim system

This paper describes a prototype system to visualize and animate 3D scenes from car accident reports, written in French. The problem of generating such a 3D simulation can be divided into two subtasks: the linguistic analysis and the virtual scene generation. As a means of communication between these two modules, we first designed a template formalism to represent a written accident report. The CARSIM system first processes written reports, gathers relevant information, and converts it into a formal description. Then, it creates the corresponding 3D scene and animates the vehicles.

The Vepsy Updated Project: Virtual Reality in Clinical Psychology

Many of us grew up with the naive assumption that couches are the best used therapeutic tools in psychotherapy. But tools for psychotherapy are evolving in a much more complex environment than a designers chaise lounge. In particular, virtual reality (VR) devices have the potential for appearing soon in many consulting rooms. The use of VR in medicine is not a novelty. Applications of virtual environments for health care have been developed in the following areas: surgical procedures (remote surgery or telepresence, augmented or enhanced surgery, and planning and simulation of procedures before surgery); preventive medicine and patient education; medical education and training; visualization of massive medical databases; and architectural design for health care facilities. However, there is a growing recognition that VR can play an important role in clinical psychology, too. To exploit and understand this potential is the main goal of the Telemedicine and Portable Virtual Environment in Clinical Psychology--VEPSY Updated--a European Community-funded research project (IST-2000-25323, http://www.vepsy.com). The project will provide innovative tools-telemedicine and portable-for the treatment of patients, clinical trials to verify their viability, and action plans for dissemination of its results to an extended audience-potential users and influential groups. The project will also develop different personal computer (PC)-based virtual reality modules to be used in clinical assessment and treatment. In particular, the developed modules will address the following pathologies: anxiety disorders; male impotence and premature ejaculation; and obesity, bulimia, and binge-eating disorders.

On the integration of skilled robot motions for productivity in manufacturing

Robots used in manufacturing today are tailored to their tasks by system integration based on expert knowledge concerning both production and machine control. For upcoming new generations of even more flexible robot solutions, in applications such as dexterous assembly, the robot setup and programming gets even more challenging. Reuse of solutions in terms of parameters, controls, process tuning, and of software modules in general then gets increasingly important. There has been valuable progress within reuse of automation solutions when machines comply with standards and behave according to nominal models. However, more flexible robots with sensor-based manipulation skills and cognitive functions for human interaction are far too complex to manage, and solutions are rarely reusable since knowledge is either implicit in imperative software or not captured in machine readable form. We propose techniques that build on existing knowledge by converting structured data into an RDF-based knowledge base. By enhancements of industrial control systems and available engineering tools, such knowledge can be gradually extended as part of the interaction during the definition of the robot task.

HMS: a predictive text entry method using bigrams

Due to the emergence of SMS messages, the significance of effective text entry on limited-size keyboards has increased. In this paper, we describe and discuss a new method to enter text more efficiently using a mobile telephone keyboard. This method, which we called HMS, predicts words from a sequence of keystrokes using a dictionary and a function combining bigram frequencies and word length. We implemented the HMS text entry method on a software-simulated mobile telephone keyboard and we compared it to a widely available commercial system. We trained the language model on a corpus of Swedish news and we evaluated the method. Although the training corpus does not reflect the language used in SMS messages, the results show a decrease by 7 to 13 percent in the number of keystrokes needed to enter a text. These figures are very encouraging even though the implementation can be optimized in several ways. The HMS text entry method can easily be transferred to other languages.