OpeNER: open polarity enhanced named entity recognition

Actualmente existe una gran cantidad de empresas ofreciendo servicios para el análisis de contenido y minería de datos de las redes sociales con el objetivo de realizar análisis de opiniones y gestión de la reputación. Un alto porcentaje de pequeñas y medianas empresas (pymes) ofrecen soluciones específicas a un sector o dominio industrial. Sin embargo, la adquisición de la necesaria tecnología básica para ofrecer tales servicios es demasiado compleja y constituye un sobrecoste demasiado alto para sus limitados recursos. El objetivo del proyecto europeo OpeNER es la reutilización y desarrollo de componentes y recursos para el procesamiento lingüístico que proporcione la tecnología necesaria para su uso industrial y/o académico.

Entity and display.

"June 6, 1995."

Pleomorphic lobular carcinoma of the breast: role of comprehensive molecular pathology in characterization of an entity

Immunohistochemical analysis of E-cadherin has changed the way lobular neoplasia is perceived. It has helped to classify difficult cases of carcinoma in situ with indeterminate features and led to the identification of new variants of lobular carcinoma. Pleomorphic lobular carcinoma (PLC) and pleomorphic lobular carcinoma in situ (PLCIS), recently described variants of invasive and in situ classic lobular carcinoma, are reported to be associated with more aggressive clinical behaviour. Although PLC/PLCIS show morphological features of classic lobular neoplasia and lack E-cadherin expression, it is still unclear whether these lesions evolve through the same genetic pathway as lobular carcinomas or are high-grade ductal neoplasms that have lost E-cadherin. Here we have analysed a case of extensive PLCIS and invasive PLC associated with areas of E-cadherin-negative carcinoma in situ with indeterminate features, using immunohistochemistry, chromogenic in situ hybridization, high-resolution comparative genomic hybridization (CGH) and array-based CGH. We observed that all lesions lacked E-cadherin and beta-catenin and showed gain of 1q and loss of 16q, features that are typical of lobular carcinomas but are not seen in high-grade ductal lesions. In addition, amplifications of c-myc and HER2 were detected in the pleomorphic components, which may account for the high-grade features in this case and the reported aggressive clinical behaviour of these lesions. Taken together, these data suggest that at least some PLCs may evolve from the same precursor or through the same genetic pathway as classic lobular carcinomas. Copyright (c) 2005 Pathological Society of Great Britain and Ireland. Published by John Wiley & Sons, Ltd.

ESpotter : adaptive named entity recognition for web browsing

Browsing constitutes an important part of the user information searching process on the Web. In this paper, we present a browser plug-in called ESpotter, which recognizes entities of various types on Web pages and highlights them according to their types to assist user browsing. ESpotter uses a range of standard named entity recognition techniques. In addition, a key new feature of ESpotter is that it addresses the problem of multiple domains on the Web by adapting lexicon and patterns to these domains.

Formalization of Structural Constraints of Relationships in Model „Entity-Relationship”

The basic conceptions of the model „entity-relationship” as entities, relationships, structural constraints of the relationships (index cardinality, participation degree, and structural constraints of kind (min, max)) are considered and formalized in terms of relations theory. For the binary relations two operators (min and max) are introduced; structural constraints are determined in terms of the operators; the main theorem about compatibility of these operators’ values on the source relation and inversion to it is given here.

Adjusting WSMO API Reference Implementation to Support More Reliable Entity Persistence

* The research has been partially supported by INFRAWEBS - IST FP62003/IST/2.3.2.3 Research Project No. 511723 and “Technologies of the Information Society for Knowledge Processing and Management” - IIT-BAS Research Project No. 010061.

Cultural Knowledge for Named Entity Disambiguation: A Graph-Based Semantic Relatedness Approach

One of the ultimate aims of Natural Language Processing is to automate the analysis of the meaning of text. A fundamental step in that direction consists in enabling effective ways to automatically link textual references to their referents, that is, real world objects. The work presented in this paper addresses the problem of attributing a sense to proper names in a given text, i.e., automatically associating words representing Named Entities with their referents. The method for Named Entity Disambiguation proposed here is based on the concept of semantic relatedness, which in this work is obtained via a graph-based model over Wikipedia. We show that, without building the traditional bag of words representation of the text, but instead only considering named entities within the text, the proposed method achieves results competitive with the state-of-the-art on two different datasets.

Select, Link and Rank: Diversified Query Expansion and Entity Ranking using Wikipedia

A search query, being a very concise grounding of user intent, could potentially have many possible interpretations. Search engines hedge their bets by diversifying top results to cover multiple such possibilities so that the user is likely to be satisfied, whatever be her intended interpretation. Diversified Query Expansion is the problem of diversifying query expansion suggestions, so that the user can specialize the query to better suit her intent, even before perusing search results. We propose a method, Select-Link-Rank, that exploits semantic information from Wikipedia to generate diversified query expansions. SLR does collective processing of terms and Wikipedia entities in an integrated framework, simultaneously diversifying query expansions and entity recommendations. SLR starts with selecting informative terms from search results of the initial query, links them to Wikipedia entities, performs a diversity-conscious entity scoring and transfers such scoring to the term space to arrive at query expansion suggestions. Through an extensive empirical analysis and user study, we show that our method outperforms the state-of-the-art diversified query expansion and diversified entity recommendation techniques.

Primary pulmonary myxoid sarcoma with EWSR1-CREB1 fusion: a new tumor entity.

We present clinicopathologic data on 10 pulmonary myxoid sarcomas, which are defined by distinctive histomorphologic features and characterized by a recurrent fusion gene, that appear to represent a distinct tumor entity at this site. The patients [7 female, 3 male; aged 27 to 67 y (mean, 45 y)] presented with local or systemic symptoms (n=5), symptoms from cerebral metastasis (1), or incidentally (2). Follow-up of 6 patients showed that 1 with brain metastasis died shortly after primary tumor resection, 1 developed a renal metastasis but is alive and well, and 4 are disease free after 1 to 15 years. All tumors involved pulmonary parenchyma, with a predominant endobronchial component in 8 and ranged from 1.5 to 4 cm. Microscopically, they were lobulated and composed of cords of polygonal, spindle, or stellate cells within myxoid stroma, morphologically reminiscent of extraskeletal myxoid chondrosarcoma. Four cases showed no or minimal atypia, 6 showed focal pleomorphism, and 5 had necrosis. Mitotic indices varied, with most tumors not exceeding 5/10 high-power fields. Tumors were immunoreactive for only vimentin and weakly focal for epithelial membrane antigen. Of 9 tumors, 7 were shown to harbor a specific EWSR1-CREB1 fusion by reverse transcription-polymerase chain reaction and direct sequencing, with 7 of 10 showing EWSR1 rearrangement by fluorescence in situ hybridization. This gene fusion has been described previously in 2 histologically and behaviorally different sarcomas: clear cell sarcoma-like tumors of the gastrointestinal tract and angiomatoid fibrous histiocytomas; however, this is a novel finding in tumors with the morphology we describe and that occur in the pulmonary region.

InfoScout: An interactive, entity centric, person search tool.

Individuals living in highly networked societies publish a large amount of personal, and potentially sensitive, information online. Web investigators can exploit such information for a variety of purposes, such as in background vetting and fraud detection. However, such investigations require a large number of expensive man hours and human effort. This paper describes InfoScout, a search tool which is intended to reduce the time it takes to identify and gather subject centric information on the Web. InfoScout collects relevance feedback information from the investigator in order to rerank search results, allowing the intended information to be discovered more quickly. Users may still direct their search as they see fit, issuing ad-hoc queries and filtering existing results by keywords. Design choices are informed by prior work and industry collaboration.

Immune-Mediated Necrotizing Myopathy: An Often Misdiagnosed Entity

Immune-mediated necrotizing myopathies (IMNM) are recognized as a subgroup of idiopathic inflammatory myopathies (IIM). IMNM are defined based on a combination of clinical presentation and laboratory studies, requiring a specific myopathological pattern on muscle biopsy for diagnosis. The authors describe a case of a patient with necrotizing myopathy, thought to be immune mediated, highlighting the challenge of its differential diagnosis. As clinical assessment and diagnostic tools sometimes fail to determine whether a necrotizing myopathy is immune mediated, leading to misdiagnosis and a compromise of the optimal therapeutic approach, distinguishing between IMNM and other myopathies is crucial.