Annotation XML et interrogation de corpus pour l’étude de la conceptualisation métaphorique

Département de linguistique et de traduction

Les modes de conceptualisation métaphorique en neuroanatomie : étude de la description anatomique du cervelet et de la moelle spinale

La présente étude s’inscrit dans une lignée de travaux de recherche en traductologie réalisés dans un cadre de sémantique cognitive et visant à dégager les modes de conceptualisation métaphorique dans les domaines de spécialité, et plus précisément dans les sciences biomédicales. Notre étude se concentre sur les modes de conceptualisation métaphorique utilisés en neuroanatomie en français, en anglais et en allemand, dans une perspective d’application à la traduction. Nous nous penchons plus spécifiquement sur la description anatomique de deux structures du système nerveux central : la moelle spinale et le cervelet. Notre objectif est de repérer et de caractériser les indices de conceptualisation métaphorique (ICM). Notre méthode s'appuie sur un corpus trilingue de textes de référence traitant de ces structures et fait appel à une annotation sémantique en langage XML, ce qui autorise une interrogation des corpus annotés au moyen du langage XQuery. Nous mettons en évidence que les ICM jouent un rôle prédominant dans la phraséologie et les dénominations propres à la description anatomique du système nerveux, comme c'est le cas en biologie cellulaire et en anatomie des muscles, des nerfs périphériques et des vaisseaux sanguins. Sous l’angle lexical, il faut distinguer les ICM prédicatifs, les ICM non prédicatifs ainsi que les ICM quasi prédicatifs. La plupart des modes de conceptualisation métaphorique préalablement repérés en biologie cellulaire et en anatomie sont également présents dans le domaine plus spécifique de la neuroanatomie. Certains ICM et modes de conceptualisation sont toutefois spécifiques à des éléments des régions étudiées. Par ailleurs, les modes de conceptualisation métaphorique en français, en anglais et en allemand sont semblables, mais sont exprimés par des réseaux lexicaux d'ICM dont la richesse varie. De plus, la composition nominale étant une des caractéristiques de l'allemand, la forme linguistique des ICM présente des caractéristiques spécifiques. Nos résultats mettent en évidence la richesse métaphorique de la neuroanatomie. Cohérents avec les résultats des études antérieures, ils enrichissent cependant la typologie des ICM et soulignent la complexité, sur les plans lexical et cognitif, de la métaphore conceptuelle.

Annotation syntaxico-sémantique des actants en corpus spécialisé

L’annotation en rôles sémantiques est une tâche qui permet d’attribuer des étiquettes de rôles telles que Agent, Patient, Instrument, Lieu, Destination etc. aux différents participants actants ou circonstants (arguments ou adjoints) d’une lexie prédicative. Cette tâche nécessite des ressources lexicales riches ou des corpus importants contenant des phrases annotées manuellement par des linguistes sur lesquels peuvent s’appuyer certaines approches d’automatisation (statistiques ou apprentissage machine). Les travaux antérieurs dans ce domaine ont porté essentiellement sur la langue anglaise qui dispose de ressources riches, telles que PropBank, VerbNet et FrameNet, qui ont servi à alimenter les systèmes d’annotation automatisés. L’annotation dans d’autres langues, pour lesquelles on ne dispose pas d’un corpus annoté manuellement, repose souvent sur le FrameNet anglais. Une ressource telle que FrameNet de l’anglais est plus que nécessaire pour les systèmes d’annotation automatisé et l’annotation manuelle de milliers de phrases par des linguistes est une tâche fastidieuse et exigeante en temps. Nous avons proposé dans cette thèse un système automatique pour aider les linguistes dans cette tâche qui pourraient alors se limiter à la validation des annotations proposées par le système. Dans notre travail, nous ne considérons que les verbes qui sont plus susceptibles que les noms d’être accompagnés par des actants réalisés dans les phrases. Ces verbes concernent les termes de spécialité d’informatique et d’Internet (ex. accéder, configurer, naviguer, télécharger) dont la structure actancielle est enrichie manuellement par des rôles sémantiques. La structure actancielle des lexies verbales est décrite selon les principes de la Lexicologie Explicative et Combinatoire, LEC de Mel’čuk et fait appel partiellement (en ce qui concerne les rôles sémantiques) à la notion de Frame Element tel que décrit dans la théorie Frame Semantics (FS) de Fillmore. Ces deux théories ont ceci de commun qu’elles mènent toutes les deux à la construction de dictionnaires différents de ceux issus des approches traditionnelles. Les lexies verbales d’informatique et d’Internet qui ont été annotées manuellement dans plusieurs contextes constituent notre corpus spécialisé. Notre système qui attribue automatiquement des rôles sémantiques aux actants est basé sur des règles ou classificateurs entraînés sur plus de 2300 contextes. Nous sommes limités à une liste de rôles restreinte car certains rôles dans notre corpus n’ont pas assez d’exemples annotés manuellement. Dans notre système, nous n’avons traité que les rôles Patient, Agent et Destination dont le nombre d’exemple est supérieur à 300. Nous avons crée une classe que nous avons nommé Autre où nous avons rassemblé les autres rôles dont le nombre d’exemples annotés est inférieur à 100. Nous avons subdivisé la tâche d’annotation en sous-tâches : identifier les participants actants et circonstants et attribuer des rôles sémantiques uniquement aux actants qui contribuent au sens de la lexie verbale. Nous avons soumis les phrases de notre corpus à l’analyseur syntaxique Syntex afin d’extraire les informations syntaxiques qui décrivent les différents participants d’une lexie verbale dans une phrase. Ces informations ont servi de traits (features) dans notre modèle d’apprentissage. Nous avons proposé deux techniques pour l’identification des participants : une technique à base de règles où nous avons extrait une trentaine de règles et une autre technique basée sur l’apprentissage machine. Ces mêmes techniques ont été utilisées pour la tâche de distinguer les actants des circonstants. Nous avons proposé pour la tâche d’attribuer des rôles sémantiques aux actants, une méthode de partitionnement (clustering) semi supervisé des instances que nous avons comparée à la méthode de classification de rôles sémantiques. Nous avons utilisé CHAMÉLÉON, un algorithme hiérarchique ascendant.

High-level concept annotation using ontology and probabilistic inference

Image annotation is a significant step towards semantic based image retrieval. Ontology is a popular approach for semantic representation and has been intensively studied for multimedia analysis. However, relations among concepts are seldom used to extract higher-level semantics. Moreover, the ontology inference is often crisp. This paper aims to enable sophisticated semantic querying of images, and thus contributes to 1) an ontology framework to contain both visual and contextual knowledge, and 2) a probabilistic inference approach to reason the high-level concepts based on different sources of information. The experiment on a natural scene database from LabelMe database shows encouraging results.

Mid-level concept learning with visual contextual ontologies and probabilistic inference for image annotation

To date, automatic recognition of semantic information such as salient objects and mid-level concepts from images is a challenging task. Since real-world objects tend to exist in a context within their environment, the computer vision researchers have increasingly incorporated contextual information for improving object recognition. In this paper, we present a method to build a visual contextual ontology from salient objects descriptions for image annotation. The ontologies include not only partOf/kindOf relations, but also spatial and co-occurrence relations. A two-step image annotation algorithm is also proposed based on ontology relations and probabilistic inference. Different from most of the existing work, we specially exploit how to combine representation of ontology, contextual knowledge and probabilistic inference. The experiments show that image annotation results are improved in the LabelMe dataset.

Asynchronicity and the ‘time envelope’ of online annotation : the case of the photosharing website, Flickr

This paper examines a sequence of asynchronous interaction on the photosharing website, Flickr. In responding to a call for a focus on the performative aspects of online annotation (Wolff & Neuwirth, 2001), we outline and apply an interaction order approach to identify temporal and cultural aspects of the setting that provide for commonality and sharing. In particular, we study the interaction as a feature of a synthetic situation (Knorr Cetina, 2009) focusing on the requirements of maintaining a sense of an ongoing discussion online. Our analysis suggests that the rhetorical system of the Flickr environment, its appropriation by participants as a context for bounded activities, and displays of commonality, affiliation, and shared access provide for a common sense of participation in a time envelope. This, in turn, is argued to be central to new processes of consociation (Schutz, 1967; Zhao, 2004) occurring in the life world of Web 2.0 environments.

Ontology-based image annotation

With regard to the long-standing problem of the semantic gap between low-level image features and high-level human knowledge, the image retrieval community has recently shifted its emphasis from low-level features analysis to high-level image semantics extrac- tion. User studies reveal that users tend to seek information using high-level semantics. Therefore, image semantics extraction is of great importance to content-based image retrieval because it allows the users to freely express what images they want. Semantic content annotation is the basis for semantic content retrieval. The aim of image anno- tation is to automatically obtain keywords that can be used to represent the content of images. The major research challenges in image semantic annotation are: what is the basic unit of semantic representation? how can the semantic unit be linked to high-level image knowledge? how can the contextual information be stored and utilized for image annotation? In this thesis, the Semantic Web technology (i.e. ontology) is introduced to the image semantic annotation problem. Semantic Web, the next generation web, aims at mak- ing the content of whatever type of media not only understandable to humans but also to machines. Due to the large amounts of multimedia data prevalent on the Web, re- searchers and industries are beginning to pay more attention to the Multimedia Semantic Web. The Semantic Web technology provides a new opportunity for multimedia-based applications, but the research in this area is still in its infancy. Whether ontology can be used to improve image annotation and how to best use ontology in semantic repre- sentation and extraction is still a worth-while investigation. This thesis deals with the problem of image semantic annotation using ontology and machine learning techniques in four phases as below. 1) Salient object extraction. A salient object servers as the basic unit in image semantic extraction as it captures the common visual property of the objects. Image segmen- tation is often used as the �rst step for detecting salient objects, but most segmenta- tion algorithms often fail to generate meaningful regions due to over-segmentation and under-segmentation. We develop a new salient object detection algorithm by combining multiple homogeneity criteria in a region merging framework. 2) Ontology construction. Since real-world objects tend to exist in a context within their environment, contextual information has been increasingly used for improving object recognition. In the ontology construction phase, visual-contextual ontologies are built from a large set of fully segmented and annotated images. The ontologies are composed of several types of concepts (i.e. mid-level and high-level concepts), and domain contextual knowledge. The visual-contextual ontologies stand as a user-friendly interface between low-level features and high-level concepts. 3) Image objects annotation. In this phase, each object is labelled with a mid-level concept in ontologies. First, a set of candidate labels are obtained by training Support Vectors Machines with features extracted from salient objects. After that, contextual knowledge contained in ontologies is used to obtain the �nal labels by removing the ambiguity concepts. 4) Scene semantic annotation. The scene semantic extraction phase is to get the scene type by using both mid-level concepts and domain contextual knowledge in ontologies. Domain contextual knowledge is used to create scene con�guration that describes which objects co-exist with which scene type more frequently. The scene con�guration is represented in a probabilistic graph model, and probabilistic inference is employed to calculate the scene type given an annotated image. To evaluate the proposed methods, a series of experiments have been conducted in a large set of fully annotated outdoor scene images. These include a subset of the Corel database, a subset of the LabelMe dataset, the evaluation dataset of localized semantics in images, the spatial context evaluation dataset, and the segmented and annotated IAPR TC-12 benchmark.

Unsupervised temporal ensemble alignment for rapid annotation

This paper presents a novel framework for the unsupervised alignment of an ensemble of temporal sequences. This approach draws inspiration from the axiom that an ensemble of temporal signals stemming from the same source/class should have lower rank when "aligned" rather than "misaligned". Our approach shares similarities with recent state of the art methods for unsupervised images ensemble alignment (e.g. RASL) which breaks the problem into a set of image alignment problems (which have well known solutions i.e. the Lucas-Kanade algorithm). Similarly, we propose a strategy for decomposing the problem of temporal ensemble alignment into a similar set of independent sequence problems which we claim can be solved reliably through Dynamic Time Warping (DTW). We demonstrate the utility of our method using the Cohn-Kanade+ dataset, to align expression onset across multiple sequences, which allows us to automate the rapid discovery of event annotations.

A transcriptomic analysis of striped catfish (Pangasianodon hypophthalmus) in response to salinity adaptation: De novo assembly, gene annotation and marker discovery

The striped catfish (Pangasianodon hypophthalmus) culture industry in the Mekong Delta in Vietnam has developed rapidly over the past decade. The culture industry now however, faces some significant challenges, especially related to climate change impacts notably from predicted extensive saltwater intrusion into many low topographical coastal provinces across the Mekong Delta. This problem highlights a need for development of culture stocks that can tolerate more saline culture environments as a response to expansion of saline water-intruded land. While a traditional artificial selection program can potentially address this need, understanding the genomic basis of salinity tolerance can assist development of more productive culture lines. The current study applied a transcriptomic approach using Ion PGM technology to generate expressed sequence tag (EST) resources from the intestine and swim bladder from striped catfish reared at a salinity level of 9 ppt which showed best growth performance. Total sequence data generated was 467.8 Mbp, consisting of 4,116,424 reads with an average length of 112 bp. De novo assembly was employed that generated 51,188 contigs, and allowed identification of 16,116 putative genes based on the GenBank non-redundant database. GO annotation, KEGG pathway mapping, and functional annotation of the EST sequences recovered with a wide diversity of biological functions and processes. In addition, more than 11,600 simple sequence repeats were also detected. This is the first comprehensive analysis of a striped catfish transcriptome, and provides a valuable genomic resource for future selective breeding programs and functional or evolutionary studies of genes that influence salinity tolerance in this important culture species.

Assembly and annotation of a non-model gastropod (Nerita melanotragus) transcriptome: a comparison of De novo assemblers

Background The sequencing, de novo assembly and annotation of transcriptome datasets generated with next generation sequencing (NGS) has enabled biologists to answer genomic questions in non-model species with unprecedented ease. Reliable and accurate de novo assembly and annotation of transcriptomes, however, is a critically important step for transcriptome assemblies generated from short read sequences. Typical benchmarks for assembly and annotation reliability have been performed with model species. To address the reliability and accuracy of de novo transcriptome assembly in non-model species, we generated an RNAseq dataset for an intertidal gastropod mollusc species, Nerita melanotragus, and compared the assembly produced by four different de novo transcriptome assemblers; Velvet, Oases, Geneious and Trinity, for a number of quality metrics and redundancy. Results Transcriptome sequencing on the Ion Torrent PGM™ produced 1,883,624 raw reads with a mean length of 133 base pairs (bp). Both the Trinity and Oases de novo assemblers produced the best assemblies based on all quality metrics including fewer contigs, increased N50 and average contig length and contigs of greater length. Overall the BLAST and annotation success of our assemblies was not high with only 15-19% of contigs assigned a putative function. Conclusions We believe that any improvement in annotation success of gastropod species will require more gastropod genome sequences, but in particular an increase in mollusc protein sequences in public databases. Overall, this paper demonstrates that reliable and accurate de novo transcriptome assemblies can be generated from short read sequencers with the right assembly algorithms. Keywords: Nerita melanotragus; De novo assembly; Transcriptome; Heat shock protein; Ion torrent

Text mining with semantic annotation : using enriched text representation for entity-oriented retrieval, semantic relation identification and text clustering

This project is a step forward in the study of text mining where enhanced text representation with semantic information plays a significant role. It develops effective methods of entity-oriented retrieval, semantic relation identification and text clustering utilizing semantically annotated data. These methods are based on enriched text representation generated by introducing semantic information extracted from Wikipedia into the input text data. The proposed methods are evaluated against several start-of-art benchmarking methods on real-life data-sets. In particular, this thesis improves the performance of entity-oriented retrieval, identifies different lexical forms for an entity relation and handles clustering documents with multiple feature spaces.

Decision support for the efficient annotation of bioacoustic events

Acoustic sensors allow scientists to scale environmental monitoring over large spatiotemporal scales. The faunal vocalisations captured by these sensors can answer ecological questions, however, identifying these vocalisations within recorded audio is difficult: automatic recognition is currently intractable and manual recognition is slow and error prone. In this paper, a semi-automated approach to call recognition is presented. An automated decision support tool is tested that assists users in the manual annotation process. The respective strengths of human and computer analysis are used to complement one another. The tool recommends the species of an unknown vocalisation and thereby minimises the need for the memorization of a large corpus of vocalisations. In the case of a folksonomic tagging system, recommending species tags also minimises the proliferation of redundant tag categories. We describe two algorithms: (1) a “naïve” decision support tool (16%–64% sensitivity) with efficiency of O(n) but which becomes unscalable as more data is added and (2) a scalable alternative with 48% sensitivity and an efficiency ofO(log n). The improved algorithm was also tested in a HTML-based annotation prototype. The result of this work is a decision support tool for annotating faunal acoustic events that may be utilised by other bioacoustics projects.

Choose wisely: Network, ontology and annotation resources for the analysis of Staphylococcus aureus omics data

Staphylococcus aureus (S. aureus) is a prominent human and livestock pathogen investigated widely using omic technologies. Critically, due to availability, low visibility or scattered resources, robust network and statistical contextualisation of the resulting data is generally under-represented. Here, we present novel meta-analyses of freely-accessible molecular network and gene ontology annotation information resources for S. aureus omics data interpretation. Furthermore, through the application of the gene ontology annotation resources we demonstrate their value and ability (or lack-there-of) to summarise and statistically interpret the emergent properties of gene expression and protein abundance changes using publically available data. This analysis provides simple metrics for network selection and demonstrates the availability and impact that gene ontology annotation selection can have on the contextualisation of bacterial omics data.

Semi-automated annotation of environmental acoustic recordings

Environmental sensors collect massive amounts of audio data. This thesis investigates computational methods to support human analysts in identifying faunal vocalisations from that audio. A series of experiments was conducted to trial the effectiveness of novel user interfaces. This research examines the rapid scanning of spectrograms, decision support tools for users, and cleaning methods for folksonomies. Together, these investigations demonstrate that providing computational support to human analysts increases their efficiency and accuracy; this allows bioacoustics projects to efficiently utilise their valuable human analysts.