Search Results: 1 - 10 of 100 matches for " "
All listed articles are free for downloading (OA Articles)
Page 1 /100
Display every page Item
Contextual Advertising through Entity Extraction  [PDF]
Asmita Joshi,Dr. J.S.Sodhi,Roopali Goel
International Journal of Engineering and Advanced Technology , 2013,
Abstract: Contextual Advertising is a type of Web advertising Content match has greater potential for content providers, publishers and advertisers, because users spend most of their time on the Web on content pages. In past researches, Contextual targeting technology works by searching the website and looks up relevant keywords But Nowadays, In contextual advertising, matching is determined automatically by the page content, which complicates the task considerably. We Proposed a System which can target the large group of consumer on internet. In Our system we make contextual targeting more relevant with Extraction of relevant entities from the web page. We extract the entities from web page, which is of interest to the consumer. We target the interest of internet user and put up the ads according to their interest. The system is designed in such a way that it can extract entities (Name, Place, Title, Location, date etc) from web page and ad publisher put up a advertise on that page which include those entities which are extracted from page. This Process will extract different types of entities, which will identify by different patterns prepared by the rules based approach. The described system able to find out the entities in many context using pattern identification. Once pattern will match entities are extracted and used by ad publisher for publishing the ads according to the context of entities. The above described method is more relevant and effective and it will target more consumers and generate revenue by advertising.
BioInfer: a corpus for information extraction in the biomedical domain
Sampo Pyysalo, Filip Ginter, Juho Heimonen, Jari Bj?rne, Jorma Boberg, Jouni J?rvinen, Tapio Salakoski
BMC Bioinformatics , 2007, DOI: 10.1186/1471-2105-8-50
Abstract: We present BioInfer (Bio Information Extraction Resource), a new public resource providing an annotated corpus of biomedical English. We describe an annotation scheme capturing named entities and their relationships along with a dependency analysis of sentence syntax. We further present ontologies defining the types of entities and relationships annotated in the corpus. Currently, the corpus contains 1100 sentences from abstracts of biomedical research articles annotated for relationships, named entities, as well as syntactic dependencies. Supporting software is provided with the corpus. The corpus is unique in the domain in combining these annotation types for a single set of sentences, and in the level of detail of the relationship annotation.We introduce a corpus targeted at protein, gene, and RNA relationships which serves as a resource for the development of information extraction systems and their components such as parsers and domain analyzers. The corpus will be maintained and further developed with a current version being available at http://www.it.utu.fi/BioInfer webcite.Recent advances in biomedical research methods have greatly accelerated the rate at which new information is published. As a result, there has been an increased interest in applying Natural Language Processing (NLP) methods to the domain of biomedical publications accessible in literature databases such as PubMed [1-4]. The attention of the BioNLP community has recently focused on Information Extraction (IE), in particular the development of IE systems for extracting protein-protein interactions.Information extraction systems automatically identify entities and their relationships from free text, producing a structured representation of the relevant information stated in the input text. Such systems can, for example, support researchers in literature searches and serve as the basis for the inference of semantic relationships, such as candidate pathways, stated across several publications.A
The "Corpus of Interactional Data" (CID) - Multimodal annotation of conversational speech" Le CID - Corpus of Interactional Data. Annotation et exploitation multimodale de parole conversationnelle  [PDF]
Roxane Bertrand,Philippe Blache,Robert Espesser,Ga?lle Ferré
Traitement Automatique des Langues , 2009,
Abstract: The understanding of language mechanisms needs to take into account very precisely the interaction between all the different domains or modalities, which implies the constitution and the development of resources. We describe here the CID (Corpus of Interactional Data), an audio-video corpus in French recorded and processed at the Laboratoire Parole et Langage (LPL). The corpus has been annotated in a multimodal perspective including phonetics, prosody, morphology, syntax, discourse and gesture studies. The first results of our studies on the CID lead to confirm the relevance of an analysis which takes into account as many linguistic fields as possible to draw up a more precise knowledge of discourse phenomena.
Combining contextual and local edges for line segment extraction in cluttered images  [PDF]
Rui F. C. Guerreiro
Computer Science , 2014,
Abstract: Automatic extraction methods typically assume that line segments are pronounced, thin, few and far between, do not cross each other, and are noise and clutter-free. Since these assumptions often fail in realistic scenarios, many line segments are not detected or are fragmented. In more severe cases, i.e., many who use the Hough Transform, extraction can fail entirely. In this paper, we propose a method that tackles these issues. Its key aspect is the combination of thresholded image derivatives obtained with filters of large and small footprints, which we denote as contextual and local edges, respectively. Contextual edges are robust to noise and we use them to select valid local edges, i.e., local edges that are of the same type as contextual ones: dark-to-bright transition of vice-versa. If the distance between valid local edges does not exceed a maximum distance threshold, we enforce connectivity by marking them and the pixels in between as edge points. This originates connected edge maps that are robust and well localized. We use a powerful two-sample statistical test to compute contextual edges, which we introduce briefly, as they are unfamiliar to the image processing community. Finally, we present experiments that illustrate, with synthetic and real images, how our method is efficient in extracting complete segments of all lengths and widths in several situations where current methods fail.
Construction of an annotated corpus to support biomedical information extraction
Paul Thompson, Syed A Iqbal, John McNaught, Sophia Ananiadou
BMC Bioinformatics , 2009, DOI: 10.1186/1471-2105-10-349
Abstract: We have defined a new scheme for annotating sentence-bound gene regulation events, centred on both verbs and nominalised verbs. For each event instance, all participants (arguments) in the same sentence are identified and assigned a semantic role from a rich set of 13 roles tailored to biomedical research articles, together with a biological concept type linked to the Gene Regulation Ontology. To our knowledge, our scheme is unique within the biomedical field in terms of the range of event arguments identified. Using the scheme, we have created the Gene Regulation Event Corpus (GREC), consisting of 240 MEDLINE abstracts, in which events relating to gene regulation and expression have been annotated by biologists. A novel method of evaluating various different facets of the annotation task showed that average inter-annotator agreement rates fall within the range of 66% - 90%.The GREC is a unique resource within the biomedical field, in that it annotates not only core relationships between entities, but also a range of other important details about these relationships, e.g., location, temporal, manner and environmental conditions. As such, it is specifically designed to support bio-specific tool and resource development. It has already been used to acquire semantic frames for inclusion within the BioLexicon (a lexical, terminological resource to aid biomedical text mining). Initial experiments have also shown that the corpus may viably be used to train IE components, such as semantic role labellers. The corpus and annotation guidelines are freely available for academic purposes.Due to the rapid advances in biomedical research, scientific literature is being published at an ever-increasing rate [1]. Without automated means, it is difficult for researchers to keep abreast of developments within biomedicine [2-6]. Text mining, which is receiving increasing interest within the biomedical field [7,8], enriches text via the addition of semantic metadata, and thus permits ta
Contextual Query Perfection by Affective Features Based Implicit Contextual Semantic Relevance Feedback in Multimedia Information Retrieval  [PDF]
Karm Veer Singh,Anil K. Tripathi
International Journal of Computer Science Issues , 2012,
Abstract: Multimedia Information may have multiple semantics depending on context, a temporal interest and user preferences. Hence we are exploiting the plausibility of context associated with semantic concept in retrieving relevance information. We are proposing an Affective Feature Based Implicit Contextual Semantic Relevance Feedback (AICSRF) to investigate whether audio and speech along with visual could determine the current context in which user wants to retrieve the information and to further investigate whether we could employ Affective Feedback as an implicit source of evidence in CSRF cycle to increase the systems contextual semantic understanding. We introduce an Emotion Recognition Unit (ERU) that comprises of spatiotemporal Gabor filter to capture spontaneous facial expression and emotional word recognition system that uses phonemes to recognize the spoken emotional words. We propose Contextual Query Perfection Scheme (CQPS) to learn, refine the current context that could be used in query perfection in RF cycle to understand the semantic of query on the basis of relevance judgment taken by ERU. Observations suggest that CQPS in AICSRF incorporating such affective features reduce the search space hence retrieval time and increase the systems contextual semantic understanding.
Automated Building Extraction from High-Resolution Satellite Imagery in Urban Areas Using Structural, Contextual, and Spectral Information  [cached]
Jin Xiaoying,Davis Curt H
EURASIP Journal on Advances in Signal Processing , 2005,
Abstract: High-resolution satellite imagery provides an important new data source for building extraction. We demonstrate an integrated strategy for identifying buildings in 1-meter resolution satellite imagery of urban areas. Buildings are extracted using structural, contextual, and spectral information. First, a series of geodesic opening and closing operations are used to build a differential morphological profile (DMP) that provides image structural information. Building hypotheses are generated and verified through shape analysis applied to the DMP. Second, shadows are extracted using the DMP to provide reliable contextual information to hypothesize position and size of adjacent buildings. Seed building rectangles are verified and grown on a finely segmented image. Next, bright buildings are extracted using spectral information. The extraction results from the different information sources are combined after independent extraction. Performance evaluation of the building extraction on an urban test site using IKONOS satellite imagery of the City of Columbia, Missouri, is reported. With the combination of structural, contextual, and spectral information, of the building areas are extracted with a quality percentage .
Discourse Analysis and Cultivation of Conversational Competence in English Class  [cached]
Zheng Zhang
International Education Studies , 2008, DOI: 10.5539/ies.v1n3p60
Abstract: The essay is to discuss in perspective of teaching how to apply the results of Discourse Analysis study to English class to train students for successful communication through taking turns, controlling turns, teaching exchange, organizing transaction, spreading topic and taking into account contextual factors as well in order to cultivate students’ conversational competence.
Using contextual and lexical features to restructure and validate the classification of biomedical concepts
Jung-Wei Fan, Hua Xu, Carol Friedman
BMC Bioinformatics , 2007, DOI: 10.1186/1471-2105-8-264
Abstract: The string-based approach achieved an error rate of 0.143, with a mean reciprocal rank of 0.907. The context-based and string-based approaches were found to be complementary, and the error rate was reduced further by applying a linear combination of the two classifiers. The advantage of combining the two approaches was especially manifested on test data with sufficient contextual features, achieving the lowest error rate of 0.055 and a mean reciprocal rank of 0.969.The lexical features provide another semantic dimension in addition to syntactic contextual features that support the classification of ontological concepts. The classification errors of each dimension can be further reduced through appropriate combination of the complementary classifiers.Biomedical ontologies such as Gene Ontology (GO) [1], the Foundational Model of Anatomy (FMA) [2], and the Unified Medical Language System (UMLS) [3,4] are important for terminology management, data sharing/integration, and decision support [5]. The ontologies specify not only the definitions of biomedical terms but also associate them with normalized concepts and semantic categories within the ontological structures. Therefore, they provide abundant lexical and semantic knowledge that is especially valuable to Natural Language Processing (NLP) systems. The overhead involved in the costly and time-consuming system development process could be substantially reduced with the aid of these knowledge sources. NLP techniques have been playing an increasingly critical role in bioinformatics research [6-8]. Spasic et al. [9] summarized various approaches that applied ontologies in biomedical NLP tasks.High-quality semantic classification is crucial for NLP and for other ontology-based applications that take advantage of conceptualization and reasoning, because the semantic accuracy can affect the correctness and/or the flexibility of the applications. We have been investigating automated methods to assist in developing and maint
EnvMine: A text-mining system for the automatic extraction of contextual information
Javier Tamames, Victor de Lorenzo
BMC Bioinformatics , 2010, DOI: 10.1186/1471-2105-11-294
Abstract: EnvMine is capable of retrieving the physicochemical variables cited in the text, by means of the accurate identification of their associated units of measurement. In this task, the system achieves a recall (percentage of items retrieved) of 92% with less than 1% error. Also a Bayesian classifier was tested for distinguishing parts of the text describing environmental characteristics from others dealing with, for instance, experimental settings.Regarding the identification of geographical locations, the system takes advantage of existing databases such as GeoNames to achieve 86% recall with 92% precision. The identification of a location includes also the determination of its exact coordinates (latitude and longitude), thus allowing the calculation of distance between the individual locations.EnvMine is a very efficient method for extracting contextual information from different text sources, like published articles or web pages. This tool can help in determining the precise location and physicochemical variables of sampling sites, thus facilitating the performance of ecological analyses. EnvMine can also help in the development of standards for the annotation of environmental features.One of the main objectives of microbial ecology is to address how the variations in environmental conditions can shape the composition and structure of prokaryotic communities. For this purpose, it is critical to count on accurate estimates of the composition of the prokaryotic communities, and on a precise description of the environment in study. Nowadays, the current knowledge about how the different environmental factors shape the distribution and diversity of prokaryotes is still scarce. Although the influence of some of these factors, salinity for instance, has been widely studied and discussed [1,2], the influence of many others, and especially the combination of different factors, is yet rather unknown.A very complete ontology, EnvO, has been developed for the annotation of the
Page 1 /100
Display every page Item

Copyright © 2008-2017 Open Access Library. All rights reserved.