INSPIRE: contributions to Invenio from the leading High Energy Physics (HEP) platform

Presentation at Open Repositories 2014, Helsinki, Finland, June 9-13, 2014

Désambiguisation de sens par modèles de contextes et son application à la Recherche d’Information

Il est connu que les problèmes d'ambiguïté de la langue ont un effet néfaste sur les résultats des systèmes de Recherche d'Information (RI). Toutefois, les efforts de recherche visant à intégrer des techniques de Désambiguisation de Sens (DS) à la RI n'ont pas porté fruit. La plupart des études sur le sujet obtiennent effectivement des résultats négatifs ou peu convaincants. De plus, des investigations basées sur l'ajout d'ambiguïté artificielle concluent qu'il faudrait une très haute précision de désambiguation pour arriver à un effet positif. Ce mémoire vise à développer de nouvelles approches plus performantes et efficaces, se concentrant sur l'utilisation de statistiques de cooccurrence afin de construire des modèles de contexte. Ces modèles pourront ensuite servir à effectuer une discrimination de sens entre une requête et les documents d'une collection. Dans ce mémoire à deux parties, nous ferons tout d'abord une investigation de la force de la relation entre un mot et les mots présents dans son contexte, proposant une méthode d'apprentissage du poids d'un mot de contexte en fonction de sa distance du mot modélisé dans le document. Cette méthode repose sur l'idée que des modèles de contextes faits à partir d'échantillons aléatoires de mots en contexte devraient être similaires. Des expériences en anglais et en japonais montrent que la force de relation en fonction de la distance suit généralement une loi de puissance négative. Les poids résultant des expériences sont ensuite utilisés dans la construction de systèmes de DS Bayes Naïfs. Des évaluations de ces systèmes sur les données de l'atelier Semeval en anglais pour la tâche Semeval-2007 English Lexical Sample, puis en japonais pour la tâche Semeval-2010 Japanese WSD, montrent que les systèmes ont des résultats comparables à l'état de l'art, bien qu'ils soient bien plus légers, et ne dépendent pas d'outils ou de ressources linguistiques. La deuxième partie de ce mémoire vise à adapter les méthodes développées à des applications de Recherche d'Information. Ces applications ont la difficulté additionnelle de ne pas pouvoir dépendre de données créées manuellement. Nous proposons donc des modèles de contextes à variables latentes basés sur l'Allocation Dirichlet Latente (LDA). Ceux-ci seront combinés à la méthodes de vraisemblance de requête par modèles de langue. En évaluant le système résultant sur trois collections de la conférence TREC (Text REtrieval Conference), nous observons une amélioration proportionnelle moyenne de 12% du MAP et 23% du GMAP. Les gains se font surtout sur les requêtes difficiles, augmentant la stabilité des résultats. Ces expériences seraient la première application positive de techniques de DS sur des tâches de RI standard.

L'atténuation statistique des surdétections d'un correcteur grammatical symbolique

Les logiciels de correction grammaticale commettent parfois des détections illégitimes (fausses alertes), que nous appelons ici surdétections. La présente étude décrit les expériences de mise au point d’un système créé pour identifier et mettre en sourdine les surdétections produites par le correcteur du français conçu par la société Druide informatique. Plusieurs classificateurs ont été entraînés de manière supervisée sur 14 types de détections faites par le correcteur, en employant des traits couvrant di-verses informations linguistiques (dépendances et catégories syntaxiques, exploration du contexte des mots, etc.) extraites de phrases avec et sans surdétections. Huit des 14 classificateurs développés sont maintenant intégrés à la nouvelle version d’un correcteur commercial très populaire. Nos expériences ont aussi montré que les modèles de langue probabilistes, les SVM et la désambiguïsation sémantique améliorent la qualité de ces classificateurs. Ce travail est un exemple réussi de déploiement d’une approche d’apprentissage machine au service d’une application langagière grand public robuste.

Apprentissage des réseaux de neurones profonds et applications en traitement automatique de la langue naturelle

En apprentissage automatique, domaine qui consiste à utiliser des données pour apprendre une solution aux problèmes que nous voulons confier à la machine, le modèle des Réseaux de Neurones Artificiels (ANN) est un outil précieux. Il a été inventé voilà maintenant près de soixante ans, et pourtant, il est encore de nos jours le sujet d'une recherche active. Récemment, avec l'apprentissage profond, il a en effet permis d'améliorer l'état de l'art dans de nombreux champs d'applications comme la vision par ordinateur, le traitement de la parole et le traitement des langues naturelles. La quantité toujours grandissante de données disponibles et les améliorations du matériel informatique ont permis de faciliter l'apprentissage de modèles à haute capacité comme les ANNs profonds. Cependant, des difficultés inhérentes à l'entraînement de tels modèles, comme les minima locaux, ont encore un impact important. L'apprentissage profond vise donc à trouver des solutions, en régularisant ou en facilitant l'optimisation. Le pré-entraînnement non-supervisé, ou la technique du ``Dropout'', en sont des exemples. Les deux premiers travaux présentés dans cette thèse suivent cette ligne de recherche. Le premier étudie les problèmes de gradients diminuants/explosants dans les architectures profondes. Il montre que des choix simples, comme la fonction d'activation ou l'initialisation des poids du réseaux, ont une grande influence. Nous proposons l'initialisation normalisée pour faciliter l'apprentissage. Le second se focalise sur le choix de la fonction d'activation et présente le rectifieur, ou unité rectificatrice linéaire. Cette étude a été la première à mettre l'accent sur les fonctions d'activations linéaires par morceaux pour les réseaux de neurones profonds en apprentissage supervisé. Aujourd'hui, ce type de fonction d'activation est une composante essentielle des réseaux de neurones profonds. Les deux derniers travaux présentés se concentrent sur les applications des ANNs en traitement des langues naturelles. Le premier aborde le sujet de l'adaptation de domaine pour l'analyse de sentiment, en utilisant des Auto-Encodeurs Débruitants. Celui-ci est encore l'état de l'art de nos jours. Le second traite de l'apprentissage de données multi-relationnelles avec un modèle à base d'énergie, pouvant être utilisé pour la tâche de désambiguation de sens.

Design And Development Of A Named Entity Based Question Answering System For Malayalam Language

This is a Named Entity Based Question Answering System for Malayalam Language. Although a vast amount of information is available today in digital form, no effective information access mechanism exists to provide humans with convenient information access. Information Retrieval and Question Answering systems are the two mechanisms available now for information access. Information systems typically return a long list of documents in response to a user’s query which are to be skimmed by the user to determine whether they contain an answer. But a Question Answering System allows the user to state his/her information need as a natural language question and receives most appropriate answer in a word or a sentence or a paragraph. This system is based on Named Entity Tagging and Question Classification. Document tagging extracts useful information from the documents which will be used in finding the answer to the question. Question Classification extracts useful information from the question to determine the type of the question and the way in which the question is to be answered. Various Machine Learning methods are used to tag the documents. Rule-Based Approach is used for Question Classification. Malayalam belongs to the Dravidian family of languages and is one of the four major languages of this family. It is one of the 22 Scheduled Languages of India with official language status in the state of Kerala. It is spoken by 40 million people. Malayalam is a morphologically rich agglutinative language and relatively of free word order. Also Malayalam has a productive morphology that allows the creation of complex words which are often highly ambiguous. Document tagging tools such as Parts-of-Speech Tagger, Phrase Chunker, Named Entity Tagger, and Compound Word Splitter are developed as a part of this research work. No such tools were available for Malayalam language. Finite State Transducer, High Order Conditional Random Field, Artificial Immunity System Principles, and Support Vector Machines are the techniques used for the design of these document preprocessing tools. This research work describes how the Named Entity is used to represent the documents. Single sentence questions are used to test the system. Overall Precision and Recall obtained are 88.5% and 85.9% respectively. This work can be extended in several directions. The coverage of non-factoid questions can be increased and also it can be extended to include open domain applications. Reference Resolution and Word Sense Disambiguation techniques are suggested as the future enhancements

Segmentation and Alignment of Speech and Sketching in a Design Environment

Sketches are commonly used in the early stages of design. Our previous system allows users to sketch mechanical systems that the computer interprets. However, some parts of the mechanical system might be too hard or too complicated to express in the sketch. Adding speech recognition to create a multimodal system would move us toward our goal of creating a more natural user interface. This thesis examines the relationship between the verbal and sketch input, particularly how to segment and align the two inputs. Toward this end, subjects were recorded while they sketched and talked. These recordings were transcribed, and a set of rules to perform segmentation and alignment was created. These rules represent the knowledge that the computer needs to perform segmentation and alignment. The rules successfully interpreted the 24 data sets that they were given.

Using triangulation to identify word senses

Word sense disambiguation is the task of determining which sense of a word is intended from its context. Previous methods have found the lack of training data and the restrictiveness of dictionaries' choices of senses to be major stumbling blocks. A robust novel algorithm is presented that uses multiple dictionaries, the Internet, clustering and triangulation to attempt to discern the most useful senses of a given word and learn how they can be disambiguated. The algorithm is explained, and some promising sample results are given.

Is children's reading “good enough”? Links between online processing and comprehension as children read syntactically ambiguous sentences

We monitored 8- and 10-year-old children’s eye movements as they read sentences containing a temporary syntactic ambiguity to obtain a detailed record of their online processing. Children showed the classic garden-path effect in online processing. Their reading was disrupted following disambiguation, relative to control sentences containing a comma to block the ambiguity, although the disruption occurred somewhat later than would be expected for mature readers. We also asked children questions to probe their comprehension of the syntactic ambiguity offline. They made more errors following ambiguous sentences than following control sentences, demonstrating that the initial incorrect parse of the garden-path sentence influenced offline comprehension. These findings are consistent with “good enough” processing effects seen in adults. While faster reading times and more regressions were generally associated with better comprehension, spending longer reading the question predicted comprehension success specifically in the ambiguous condition. This suggests that reading the question prompted children to reconstruct the sentence and engage in some form of processing, which in turn increased the likelihood of comprehension success. Older children were more sensitive to the syntactic function of commas, and, overall, they were faster and more accurate than younger children.

Effects of a multi-session Cognitive Bias Modification program on interpretative biases and social anxiety symptoms in a sample of Iranian socially-anxious students

This study examines the effects of a multi-session Cognitive Bias Modification (CBM) program on interpretative biases and social anxiety in an Iranian sample. Thirty-six volunteers with a high score on social anxiety measures were recruited from a student population and randomly allocated into the experimental and control groups. In the experimental group, participants received 4 sessions of positive CBM for interpretative biases (CBM-I) over 2 weeks in the laboratory. Participants in the control condition completed a neutral task matched the active CBM-I intervention in format and duration but did not encourage positive disambiguation of socially ambiguous scenarios. The results indicated that after training the positive CBM-I group exhibited more positive (and less negative) interpretations of ambiguous scenarios and less social anxiety symptoms relative to the control condition at both 1 week post-test and 7 weeks follow-up. It is suggested that clinical trials are required to establish the clinical efficacy of this intervention for social anxiety.

The “pain matrix” in pain-free individuals

Human functional imaging provides a correlative picture of brain activity during pain. A particular set of central nervous system structures (eg, the anterior cingulate cortex, thalamus, and insula) consistently respond to transient nociceptive stimuli causing pain. Activation of this so-called pain matrix or pain signature has been related to perceived pain intensity, both within and between individuals,1,2 and is now considered a candidate biomarker for pain in medicolegal settings and a tool for drug discovery. The pain-specific interpretation of such functional magnetic resonance imaging (fMRI) responses, although logically flawed,3,4 remains pervasive. For example, a 2015 review states that “the most likely interpretation of activity in the pain matrix seems to be pain.”4 Demonstrating the nonspecificity of the pain matrix requires ruling out the presence of pain when highly salient sensory stimuli are presented. In this study, we administered noxious mechanical stimuli to individuals with congenital insensitivity to pain and sampled their brain activity with fMRI. Loss-of-function SCN9A mutations in these individuals abolishes sensory neuron sodium channel Nav1.7 activity, resulting in pain insensitivity through an impaired peripheral drive that leaves tactile percepts fully intact.5 This allows complete experimental disambiguation of sensory responses and painful sensations

Lógica condicional

The main goal of this work is to clarify the central concepts involved in the study of formalization of conditional sentences. More specifically, it has been done a comparative analysis of the two greater and more traditional proposals of conditional formalization (Lewis 1973c e Adams 1975). These proposals were responsible for the creation of a way of analysis that still present in the current debate about this subject. This work pursues to explain the principal assumptions held within these proposals. According to certain disambiguation techniques from Bennett (2003) and Lycan (2005), this work tries to explicit how these assumptions connect to the aims sought by the initial approaches. The following results show that there is a not declared presumption, the definition of the object of study of these theories, i.e., the definition of conditional sentence. This work argues that despite of not explicitly declared the definition of the study object has a central role in the intelligibility of the debate itself

Homonymy in natural language processes: A representation using Pustejovsky's Qualia Structure and ontological information

This paper presents a proposal for the semantic treatment of ambiguous homographic forms in Brazilian Portuguese, and to offer linguistic strategies for its computational implementation in Systems of Natural Language Processing (SNLP). Pustejovsky's Generative Lexicon was used as a theoretical model. From this model, the Qualia Structure - QS (and the Formal, Telic, Agentive and Constitutive roles) was selected as one of the linguistic and semantic expedients for the achievement of disambiguation of homonym forms. So that analyzed and treated data could be manipulated, we elaborated a Lexical Knowledge Base (LKB) where lexical items are correlated and interconnected by different kinds of semantic relations in the QS and ontological information.

As ambiguidades linguísticas no inglês e a tradução automática inglês-português: um estudo exploratório

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Abordagem para o desenvolvimento de um etiquetador de alta acurácia para o Português do Brasil

A etiquetagem morfossintática é uma tarefa básica requerida por muitas aplicações de processamento de linguagem natural, tais como análise gramatical e tradução automática, e por aplicações de processamento de fala, por exemplo, síntese de fala. Essa tarefa consiste em etiquetar palavras em uma sentença com as suas categorias gramaticais. Apesar dessas aplicações requererem etiquetadores que demandem maior precisão, os etiquetadores do estado da arte ainda alcançam acurácia de 96 a 97%. Nesta tese, são investigados recursos de corpus e de software para o desenvolvimento de um etiquetador com acurácia superior à do estado da arte para o português brasileiro. Centrada em uma solução híbrida que combina etiquetagem probabilística com etiquetagem baseada em regras, a proposta de tese se concentra em um estudo exploratório sobre o método de etiquetagem, o tamanho, a qualidade, o conjunto de etiquetas e o gênero dos corpora de treinamento e teste, além de avaliar a desambiguização de palavras novas ou desconhecidas presentes nos textos a serem etiquetados. Quatro corpora foram usados nos experimentos: CETENFolha, Bosque CF 7.4, Mac-Morpho e Selva Científica. O modelo de etiquetagem proposto partiu do uso do método de aprendizado baseado em transformação(TBL) ao qual foram adicionadas três estratégias, combinadas em uma arquitetura que integra as saídas (textos etiquetados) de duas ferramentas de uso livre, o TreeTagger e o -TBL, com os módulos adicionados ao modelo. No modelo de etiquetador treinado com o corpus Mac-Morpho, de gênero jornalístico, foram obtidas taxas de acurácia de 98,05% na etiquetagem de textos do Mac-Morpho e 98,27% em textos do Bosque CF 7.4, ambos de gênero jornalístico. Avaliou-se também o desempenho do modelo de etiquetador híbrido proposto na etiquetagem de textos do corpus Selva Científica, de gênero científico. Foram identificadas necessidades de ajustes no etiquetador e nos corpora e, como resultado, foram alcançadas taxas de acurácia de 98,07% no Selva Científica, 98,06% no conjunto de teste do Mac-Morpho e 98,30% em textos do Bosque CF 7.4. Esses resultados são significativos, pois as taxas de acurácia alcançadas são superiores às do estado da arte, validando o modelo proposto em busca de um etiquetador morfossintático mais confiável.

Unveiling the relationship between complex networks metrics and word senses

The automatic disambiguation of word senses (i.e., the identification of which of the meanings is used in a given context for a word that has multiple meanings) is essential for such applications as machine translation and information retrieval, and represents a key step for developing the so-called Semantic Web. Humans disambiguate words in a straightforward fashion, but this does not apply to computers. In this paper we address the problem of Word Sense Disambiguation (WSD) by treating texts as complex networks, and show that word senses can be distinguished upon characterizing the local structure around ambiguous words. Our goal was not to obtain the best possible disambiguation system, but we nevertheless found that in half of the cases our approach outperforms traditional shallow methods. We show that the hierarchical connectivity and clustering of words are usually the most relevant features for WSD. The results reported here shed light on the relationship between semantic and structural parameters of complex networks. They also indicate that when combined with traditional techniques the complex network approach may be useful to enhance the discrimination of senses in large texts. Copyright (C) EPLA, 2012