Quality of Web-based information on obsessive compulsive disorder.

BACKGROUND: The Internet is increasingly used as a source of information for mental health issues. The burden of obsessive compulsive disorder (OCD) may lead persons with diagnosed or undiagnosed OCD, and their relatives, to search for good quality information on the Web. This study aimed to evaluate the quality of Web-based information on English-language sites dealing with OCD and to compare the quality of websites found through a general and a medically specialized search engine. METHODS: Keywords related to OCD were entered into Google and OmniMedicalSearch. Websites were assessed on the basis of accountability, interactivity, readability, and content quality. The "Health on the Net" (HON) quality label and the Brief DISCERN scale score were used as possible content quality indicators. Of the 235 links identified, 53 websites were analyzed. RESULTS: The content quality of the OCD websites examined was relatively good. The use of a specialized search engine did not offer an advantage in finding websites with better content quality. A score ≥16 on the Brief DISCERN scale is associated with better content quality. CONCLUSION: This study shows the acceptability of the content quality of OCD websites. There is no advantage in searching for information with a specialized search engine rather than a general one. Practical implications: The Internet offers a number of high quality OCD websites. It remains critical, however, to have a provider-patient talk about the information found on the Web.

Confabulation in schizophrenia: a neuropsychological study.

Confabulation has been documented in schizophrenia, but its neuropsychological correlates appear to be different from those of confabulation in neurological disease states. Forty-five schizophrenic patients and 37 controls were administered a task requiring them to recall fables. They also underwent testing with a range of memory and executive tasks. The patients with schizophrenia produced significantly more confabulations than the controls. After correcting for multiple comparisons, confabulation was not significantly associated with memory impairment, and was associated with impairment on only one of eight executive measures, the Brixton Test. Confabulation scores were also associated with impairment on two semantic memory tests. Confabulation was correlated with intrusion errors in recall, but not false positive errors in a recognition task. The findings suggest that confabulation in schizophrenia is unrelated to the episodic memory impairment seen in the disorder. However, the association with a circumscribed deficit in executive function could be consistent with a defective strategic retrieval account of confabulation similar to that of Moscovitch and co-workers, interacting with defective semantic memory.

Quality of Web-based information on obsessive compulsive disorder.

BACKGROUND: The Internet is increasingly used as a source of information for mental health issues. The burden of obsessive compulsive disorder (OCD) may lead persons with diagnosed or undiagnosed OCD, and their relatives, to search for good quality information on the Web. This study aimed to evaluate the quality of Web-based information on English-language sites dealing with OCD and to compare the quality of websites found through a general and a medically specialized search engine. METHODS: Keywords related to OCD were entered into Google and OmniMedicalSearch. Websites were assessed on the basis of accountability, interactivity, readability, and content quality. The "Health on the Net" (HON) quality label and the Brief DISCERN scale score were used as possible content quality indicators. Of the 235 links identified, 53 websites were analyzed. RESULTS: The content quality of the OCD websites examined was relatively good. The use of a specialized search engine did not offer an advantage in finding websites with better content quality. A score ≥16 on the Brief DISCERN scale is associated with better content quality. CONCLUSION: This study shows the acceptability of the content quality of OCD websites. There is no advantage in searching for information with a specialized search engine rather than a general one. Practical implications: The Internet offers a number of high quality OCD websites. It remains critical, however, to have a provider-patient talk about the information found on the Web.

El lenguaje de la interrogación: una gramática formal para la recuperación de la información

El conocimiento del lenguaje de interrogación es una herramienta imprescindible para la recuperación de información. En este artículo se ofrece una gramática formal (sintaxis y semántica) para ese tipo de lenguaje. Esta gramática nos permite, por un lado, conocer el lenguaje de interrogación desde un plano sistemático y conceptual y, por otro lado, nos permite obtener ciertos beneficios prácticos de tipo sintáctico y de tipo semántico relacionados con los procesos de recuperación de información.

Mynodbcsv: Lightweight Zero-Config Database Solution for Handling Very Large CSV Files.

Volumes of data used in science and industry are growing rapidly. When researchers face the challenge of analyzing them, their format is often the first obstacle. Lack of standardized ways of exploring different data layouts requires an effort each time to solve the problem from scratch. Possibility to access data in a rich, uniform manner, e.g. using Structured Query Language (SQL) would offer expressiveness and user-friendliness. Comma-separated values (CSV) are one of the most common data storage formats. Despite its simplicity, with growing file size handling it becomes non-trivial. Importing CSVs into existing databases is time-consuming and troublesome, or even impossible if its horizontal dimension reaches thousands of columns. Most databases are optimized for handling large number of rows rather than columns, therefore, performance for datasets with non-typical layouts is often unacceptable. Other challenges include schema creation, updates and repeated data imports. To address the above-mentioned problems, I present a system for accessing very large CSV-based datasets by means of SQL. It's characterized by: "no copy" approach - data stay mostly in the CSV files; "zero configuration" - no need to specify database schema; written in C++, with boost [1], SQLite [2] and Qt [3], doesn't require installation and has very small size; query rewriting, dynamic creation of indices for appropriate columns and static data retrieval directly from CSV files ensure efficient plan execution; effortless support for millions of columns; due to per-value typing, using mixed text/numbers data is easy; very simple network protocol provides efficient interface for MATLAB and reduces implementation time for other languages. The software is available as freeware along with educational videos on its website [4]. It doesn't need any prerequisites to run, as all of the libraries are included in the distribution package. I test it against existing database solutions using a battery of benchmarks and discuss the results.

Evaluation de la qualité des sites internet francophones traitant de la dépendance à l'alcool [Assessing the quality of French language web sites pertaining to alcohol dependency]

The objective of this article is to systematically assess the quality of web-based information in French language on the alcohol dependence. The authors analysed, using a standardised pro forma, the 20 most highly ranked pages identified by 3 common internet search engines using 2 keywords. Results show that a total of 45 sites were analysed. The authors conclude that the overall quality of the sites was relatively poor, especially for the description of possible treatments, however with a wide variability. Content quality was not correlated with other aspects of quality such as interactivity, aesthetic or accountability.

Ontologia de Twitter : El primer pas per inferir informació dels tweets

En aquest treball es realitza un estudi sobre l'estat de l'art de la web semàntica i els seus estàndards actuals, més concretament sobre ontologies. Descriu també el procés pràctic emprat pel disseny i la implementació d'una ontologia en el domini concret de Twitter, en format OWL, fent servir l'aplicació Protégé per a la seva creació. Finalment explica la creació (captura de requeriments, disseny i implementació) d'una aplicació capaç d'obtenir dades reals de Twitter, processar-les per extreure'n la informació rellevant i emmagatzemar-la a la ontologia creada.

Sumeat käännösmenetelmät läheisten sukulaiskielten välisessä tiedonhaussa

Summary : Fuzzy translation techniques in cross-language information retrieval between closely related languages

New kernel functions and learning methods for text and data mining

Recent advances in machine learning methods enable increasingly the automatic construction of various types of computer assisted methods that have been difficult or laborious to program by human experts. The tasks for which this kind of tools are needed arise in many areas, here especially in the fields of bioinformatics and natural language processing. The machine learning methods may not work satisfactorily if they are not appropriately tailored to the task in question. However, their learning performance can often be improved by taking advantage of deeper insight of the application domain or the learning problem at hand. This thesis considers developing kernel-based learning algorithms incorporating this kind of prior knowledge of the task in question in an advantageous way. Moreover, computationally efficient algorithms for training the learning machines for specific tasks are presented. In the context of kernel-based learning methods, the incorporation of prior knowledge is often done by designing appropriate kernel functions. Another well-known way is to develop cost functions that fit to the task under consideration. For disambiguation tasks in natural language, we develop kernel functions that take account of the positional information and the mutual similarities of words. It is shown that the use of this information significantly improves the disambiguation performance of the learning machine. Further, we design a new cost function that is better suitable for the task of information retrieval and for more general ranking problems than the cost functions designed for regression and classification. We also consider other applications of the kernel-based learning algorithms such as text categorization, and pattern recognition in differential display. We develop computationally efficient algorithms for training the considered learning machines with the proposed kernel functions. We also design a fast cross-validation algorithm for regularized least-squares type of learning algorithm. Further, an efficient version of the regularized least-squares algorithm that can be used together with the new cost function for preference learning and ranking tasks is proposed. In summary, we demonstrate that the incorporation of prior knowledge is possible and beneficial, and novel advanced kernels and cost functions can be used in algorithms efficiently.

Search Interfaces on the Web: Querying and Characterizing

Current-day web search engines (e.g., Google) do not crawl and index a significant portion of theWeb and, hence, web users relying on search engines only are unable to discover and access a large amount of information from the non-indexable part of the Web. Specifically, dynamic pages generated based on parameters provided by a user via web search forms (or search interfaces) are not indexed by search engines and cannot be found in searchers’ results. Such search interfaces provide web users with an online access to myriads of databases on the Web. In order to obtain some information from a web database of interest, a user issues his/her query by specifying query terms in a search form and receives the query results, a set of dynamic pages that embed required information from a database. At the same time, issuing a query via an arbitrary search interface is an extremely complex task for any kind of automatic agents including web crawlers, which, at least up to the present day, do not even attempt to pass through web forms on a large scale. In this thesis, our primary and key object of study is a huge portion of the Web (hereafter referred as the deep Web) hidden behind web search interfaces. We concentrate on three classes of problems around the deep Web: characterization of deep Web, finding and classifying deep web resources, and querying web databases. Characterizing deep Web: Though the term deep Web was coined in 2000, which is sufficiently long ago for any web-related concept/technology, we still do not know many important characteristics of the deep Web. Another matter of concern is that surveys of the deep Web existing so far are predominantly based on study of deep web sites in English. One can then expect that findings from these surveys may be biased, especially owing to a steady increase in non-English web content. In this way, surveying of national segments of the deep Web is of interest not only to national communities but to the whole web community as well. In this thesis, we propose two new methods for estimating the main parameters of deep Web. We use the suggested methods to estimate the scale of one specific national segment of the Web and report our findings. We also build and make publicly available a dataset describing more than 200 web databases from the national segment of the Web. Finding deep web resources: The deep Web has been growing at a very fast pace. It has been estimated that there are hundred thousands of deep web sites. Due to the huge volume of information in the deep Web, there has been a significant interest to approaches that allow users and computer applications to leverage this information. Most approaches assumed that search interfaces to web databases of interest are already discovered and known to query systems. However, such assumptions do not hold true mostly because of the large scale of the deep Web – indeed, for any given domain of interest there are too many web databases with relevant content. Thus, the ability to locate search interfaces to web databases becomes a key requirement for any application accessing the deep Web. In this thesis, we describe the architecture of the I-Crawler, a system for finding and classifying search interfaces. Specifically, the I-Crawler is intentionally designed to be used in deepWeb characterization studies and for constructing directories of deep web resources. Unlike almost all other approaches to the deep Web existing so far, the I-Crawler is able to recognize and analyze JavaScript-rich and non-HTML searchable forms. Querying web databases: Retrieving information by filling out web search forms is a typical task for a web user. This is all the more so as interfaces of conventional search engines are also web forms. At present, a user needs to manually provide input values to search interfaces and then extract required data from the pages with results. The manual filling out forms is not feasible and cumbersome in cases of complex queries but such kind of queries are essential for many web searches especially in the area of e-commerce. In this way, the automation of querying and retrieving data behind search interfaces is desirable and essential for such tasks as building domain-independent deep web crawlers and automated web agents, searching for domain-specific information (vertical search engines), and for extraction and integration of information from various deep web resources. We present a data model for representing search interfaces and discuss techniques for extracting field labels, client-side scripts and structured data from HTML pages. We also describe a representation of result pages and discuss how to extract and store results of form queries. Besides, we present a user-friendly and expressive form query language that allows one to retrieve information behind search interfaces and extract useful data from the result pages based on specified conditions. We implement a prototype system for querying web databases and describe its architecture and components design.

Biomedical Event Extraction with Machine Learning

Biomedical natural language processing (BioNLP) is a subfield of natural language processing, an area of computational linguistics concerned with developing programs that work with natural language: written texts and speech. Biomedical relation extraction concerns the detection of semantic relations such as protein-protein interactions (PPI) from scientific texts. The aim is to enhance information retrieval by detecting relations between concepts, not just individual concepts as with a keyword search. In recent years, events have been proposed as a more detailed alternative for simple pairwise PPI relations. Events provide a systematic, structural representation for annotating the content of natural language texts. Events are characterized by annotated trigger words, directed and typed arguments and the ability to nest other events. For example, the sentence “Protein A causes protein B to bind protein C” can be annotated with the nested event structure CAUSE(A, BIND(B, C)). Converted to such formal representations, the information of natural language texts can be used by computational applications. Biomedical event annotations were introduced by the BioInfer and GENIA corpora, and event extraction was popularized by the BioNLP'09 Shared Task on Event Extraction. In this thesis we present a method for automated event extraction, implemented as the Turku Event Extraction System (TEES). A unified graph format is defined for representing event annotations and the problem of extracting complex event structures is decomposed into a number of independent classification tasks. These classification tasks are solved using SVM and RLS classifiers, utilizing rich feature representations built from full dependency parsing. Building on earlier work on pairwise relation extraction and using a generalized graph representation, the resulting TEES system is capable of detecting binary relations as well as complex event structures. We show that this event extraction system has good performance, reaching the first place in the BioNLP'09 Shared Task on Event Extraction. Subsequently, TEES has achieved several first ranks in the BioNLP'11 and BioNLP'13 Shared Tasks, as well as shown competitive performance in the binary relation Drug-Drug Interaction Extraction 2011 and 2013 shared tasks. The Turku Event Extraction System is published as a freely available open-source project, documenting the research in detail as well as making the method available for practical applications. In particular, in this thesis we describe the application of the event extraction method to PubMed-scale text mining, showing how the developed approach not only shows good performance, but is generalizable and applicable to large-scale real-world text mining projects. Finally, we discuss related literature, summarize the contributions of the work and present some thoughts on future directions for biomedical event extraction. This thesis includes and builds on six original research publications. The first of these introduces the analysis of dependency parses that leads to development of TEES. The entries in the three BioNLP Shared Tasks, as well as in the DDIExtraction 2011 task are covered in four publications, and the sixth one demonstrates the application of the system to PubMed-scale text mining.

Étude sur l’influence du vocabulaire utilisé pour l’indexation des images en contexte de repérage multilingue

Depuis quelques années, Internet est devenu un média incontournable pour la diffusion de ressources multilingues. Cependant, les différences linguistiques constituent souvent un obstacle majeur aux échanges de documents scientifiques, culturels, pédagogiques et commerciaux. En plus de cette diversité linguistique, on constate le développement croissant de bases de données et de collections composées de différents types de documents textuels ou multimédias, ce qui complexifie également le processus de repérage documentaire. En général, on considère l’image comme « libre » au point de vue linguistique. Toutefois, l’indexation en vocabulaire contrôlé ou libre (non contrôlé) confère à l’image un statut linguistique au même titre que tout document textuel, ce qui peut avoir une incidence sur le repérage. Le but de notre recherche est de vérifier l’existence de différences entre les caractéristiques de deux approches d’indexation pour les images ordinaires représentant des objets de la vie quotidienne, en vocabulaire contrôlé et en vocabulaire libre, et entre les résultats obtenus au moment de leur repérage. Cette étude suppose que les deux approches d’indexation présentent des caractéristiques communes, mais également des différences pouvant influencer le repérage de l’image. Cette recherche permet de vérifier si l’une ou l’autre de ces approches d’indexation surclasse l’autre, en termes d’efficacité, d’efficience et de satisfaction du chercheur d’images, en contexte de repérage multilingue. Afin d’atteindre le but fixé par cette recherche, deux objectifs spécifiques sont définis : identifier les caractéristiques de chacune des deux approches d’indexation de l’image ordinaire représentant des objets de la vie quotidienne pouvant influencer le repérage, en contexte multilingue et exposer les différences sur le plan de l’efficacité, de l’efficience et de la satisfaction du chercheur d’images à repérer des images ordinaires représentant des objets de la vie quotidienne indexées à l’aide d’approches offrant des caractéristiques variées, en contexte multilingue. Trois modes de collecte des données sont employés : l’analyse des termes utilisés pour l’indexation des images, la simulation du repérage d’un ensemble d’images indexées selon chacune des formes d’indexation à l’étude réalisée auprès de soixante répondants, et le questionnaire administré aux participants pendant et après la simulation du repérage. Quatre mesures sont définies pour cette recherche : l’efficacité du repérage d’images, mesurée par le taux de succès du repérage calculé à l’aide du nombre d’images repérées; l’efficience temporelle, mesurée par le temps, en secondes, utilisé par image repérée; l’efficience humaine, mesurée par l’effort humain, en nombre de requêtes formulées par image repérée et la satisfaction du chercheur d’images, mesurée par son autoévaluation suite à chaque tâche de repérage effectuée. Cette recherche montre que sur le plan de l’indexation de l’image ordinaire représentant des objets de la vie quotidienne, les approches d’indexation étudiées diffèrent fondamentalement l’une de l’autre, sur le plan terminologique, perceptuel et structurel. En outre, l’analyse des caractéristiques des deux approches d’indexation révèle que si la langue d’indexation est modifiée, les caractéristiques varient peu au sein d’une même approche d’indexation. Finalement, cette recherche souligne que les deux approches d’indexation à l’étude offrent une performance de repérage des images ordinaires représentant des objets de la vie quotidienne différente sur le plan de l’efficacité, de l’efficience et de la satisfaction du chercheur d’images, selon l’approche et la langue utilisées pour l’indexation.

Élaboration d'un corpus étalon pour l'évaluation d'extracteurs de termes

Ce travail porte sur la construction d’un corpus étalon pour l’évaluation automatisée des extracteurs de termes. Ces programmes informatiques, conçus pour extraire automatiquement les termes contenus dans un corpus, sont utilisés dans différentes applications, telles que la terminographie, la traduction, la recherche d’information, l’indexation, etc. Ainsi, leur évaluation doit être faite en fonction d’une application précise. Une façon d’évaluer les extracteurs consiste à annoter toutes les occurrences des termes dans un corpus, ce qui nécessite un protocole de repérage et de découpage des unités terminologiques. À notre connaissance, il n’existe pas de corpus annoté bien documenté pour l’évaluation des extracteurs. Ce travail vise à construire un tel corpus et à décrire les problèmes qui doivent être abordés pour y parvenir. Le corpus étalon que nous proposons est un corpus entièrement annoté, construit en fonction d’une application précise, à savoir la compilation d’un dictionnaire spécialisé de la mécanique automobile. Ce corpus rend compte de la variété des réalisations des termes en contexte. Les termes sont sélectionnés en fonction de critères précis liés à l’application, ainsi qu’à certaines propriétés formelles, linguistiques et conceptuelles des termes et des variantes terminologiques. Pour évaluer un extracteur au moyen de ce corpus, il suffit d’extraire toutes les unités terminologiques du corpus et de comparer, au moyen de métriques, cette liste à la sortie de l’extracteur. On peut aussi créer une liste de référence sur mesure en extrayant des sous-ensembles de termes en fonction de différents critères. Ce travail permet une évaluation automatique des extracteurs qui tient compte du rôle de l’application. Cette évaluation étant reproductible, elle peut servir non seulement à mesurer la qualité d’un extracteur, mais à comparer différents extracteurs et à améliorer les techniques d’extraction.

Modeling High-Dimensional Audio Sequences with Recurrent Neural Networks

Cette thèse étudie des modèles de séquences de haute dimension basés sur des réseaux de neurones récurrents (RNN) et leur application à la musique et à la parole. Bien qu'en principe les RNN puissent représenter les dépendances à long terme et la dynamique temporelle complexe propres aux séquences d'intérêt comme la vidéo, l'audio et la langue naturelle, ceux-ci n'ont pas été utilisés à leur plein potentiel depuis leur introduction par Rumelhart et al. (1986a) en raison de la difficulté de les entraîner efficacement par descente de gradient. Récemment, l'application fructueuse de l'optimisation Hessian-free et d'autres techniques d'entraînement avancées ont entraîné la recrudescence de leur utilisation dans plusieurs systèmes de l'état de l'art. Le travail de cette thèse prend part à ce développement. L'idée centrale consiste à exploiter la flexibilité des RNN pour apprendre une description probabiliste de séquences de symboles, c'est-à-dire une information de haut niveau associée aux signaux observés, qui en retour pourra servir d'à priori pour améliorer la précision de la recherche d'information. Par exemple, en modélisant l'évolution de groupes de notes dans la musique polyphonique, d'accords dans une progression harmonique, de phonèmes dans un énoncé oral ou encore de sources individuelles dans un mélange audio, nous pouvons améliorer significativement les méthodes de transcription polyphonique, de reconnaissance d'accords, de reconnaissance de la parole et de séparation de sources audio respectivement. L'application pratique de nos modèles à ces tâches est détaillée dans les quatre derniers articles présentés dans cette thèse. Dans le premier article, nous remplaçons la couche de sortie d'un RNN par des machines de Boltzmann restreintes conditionnelles pour décrire des distributions de sortie multimodales beaucoup plus riches. Dans le deuxième article, nous évaluons et proposons des méthodes avancées pour entraîner les RNN. Dans les quatre derniers articles, nous examinons différentes façons de combiner nos modèles symboliques à des réseaux profonds et à la factorisation matricielle non-négative, notamment par des produits d'experts, des architectures entrée/sortie et des cadres génératifs généralisant les modèles de Markov cachés. Nous proposons et analysons également des méthodes d'inférence efficaces pour ces modèles, telles la recherche vorace chronologique, la recherche en faisceau à haute dimension, la recherche en faisceau élagué et la descente de gradient. Finalement, nous abordons les questions de l'étiquette biaisée, du maître imposant, du lissage temporel, de la régularisation et du pré-entraînement.