Now showing items 99-118 of 275

  • Identification of bilingual terms from monolingual documents for statistical machine translation 

    Arcan, Mihael; Giuliano, Claudio; Turchi, Marco; Buitelaar, Paul (Association for Computational Linguistics, 2014-08-23)
    The automatic translation of domain-specific documents is often a hard task for generic Statistical Machine Translation (SMT) systems, which are not able to correctly translate the large number of terms encountered in the ...
  • Identifying equivalent relation paths in knowledge graphs 

    Mohamed, Sameh K.; Muñoz, Emir; Nováček, Vít; Vandenbussche, Pierre-Yves (Springer Verlag, 2017-06-19)
    Relation paths are sequences of relations with inverse that allow for complete exploration of knowledge graphs in a two-way unconstrained manner. They are powerful enough to encode complex relationships between entities ...
  • Identifying main obstacles for statistical machine translation of morphologically rich South Slavic languages 

    Popovic, Maja; Arcan, Mihael (European Association for Machine Translation, 2015-05-11)
    The best way to improve a statistical machine translation system is to identify concrete problems causing translation errors and address them. Many of these problems are related to the characteristics of the involved ...
  • IKHarvester Informal eLearning with SemanticWeb Harvesting 

    Jankowski, Jacek; Westerski, Adam; Kruk, Sebastian Ryszard; Nagle, Tadhg; Dobrzanski, Jaroslaw (IEEE, 2008)
    Only recently, researchers and practitioners alike have begun to fully understand the potential of eLearning and have concentrated on new tools and technologies for creating, capturing and distributing knowledge. In order ...
  • Implicit and explicit aspect extraction in financial microblogs 

    Gaillat, Thomas; Stearns, Bernardo; McDermott, Ross; Sridhar, Gopal; Zarrouk, Manel; Davis, Brian (Association for Computational Linguistics, 2018-07-15)
    This paper focuses on aspect extraction which is a sub-task of Aspect-based Sentiment Analysis. The goal is to report an extraction method of financial aspects in microblog messages. Our approach uses a stock-investment ...
  • Imprecise Empirical Ontology Refinement: Application to Taxonomy Acquisition 

    Nováček, Vít (INSTICC, 2007)
    The significance of uncertainty representation has become obvious in the Semantic Web community recently. This paper presents new results of our research on uncertainty incorporation into ontologies created automatically ...
  • Improving wordnets for under-resourced languages using machine translation 

    Chakravarthi, Bharathi Raja; Arcan, Mihael; McCrae, John P. (Global Wordnet Association, 2018-01-08)
    Wordnets are extensively used in natural language processing, but the current approaches for manually building a wordnet from scratch involves large research groups for a long period of time, which are typically not ...
  • Inferring translation candidates for multilingual dictionary generation with multi-way neural machine translation 

    Arcan, Mihael; Torregrosa, Daniel; Ahmadi, Sina; McCrae, John P. (National University of Ireland, Galway, 2019-05-20)
    In the widely-connected digital world, multilingual lexical resources are one of the most important resources, for natural language processing applications, including information retrieval, question answering or knowledge ...
  • Infrastructure for data processing in large-scale interconnected sensor network 

    Aberer, Karl; Hauswirth, Manfred (2007)
    With the price of wireless sensor technologies diminishing rapidly we can expect large numbers of autonomous sensor networks being deployed in the near future. These sensor networks will typically not remain isolated but ...
  • Innovative Solution to Service Discovery and Integration using WSMOLX 

    Zaremba, Maciej; Zaharia, Raluca; Vitvar, Tomas (Springer, 2008)
    WSMX is a Semantic Web services broker enabling dynamic discovery and agile B2B integration of enterprise services. Our framework enables on-demand service discovery encompassing frequently changing aspects like fine-grained ...
  • Instance selection for online automatic post-editing in a multi-domain scenario 

    Chatterjee, Rajen; Arcan, Mihael; Negri, Matteo; Turchi, Marco (Association for Machine Translation in the Americas, 2016)
    In recent years, several end-to-end online translation systems have been proposed to successfully incorporate human post-editing feedback in the translation workflow. The performance of these systems in a multi-domain ...
  • Integrating Developer-related information across Open Source Repositories 

    Iqbal, Aftab; Hausenblas, Michael (2012)
    Software developers use various software repositories in order to interact with each other or to solve software related problems. They are required to adopt an identity for each of the software repositories they wanted to ...
  • Integrating Developer-related information across Open Source Repositories 

    Aftab Iqbal and Michael Hausenblas (2012)
    Software developers use various software repositories in order to interact with each other or to solve software related problems. They are required to adopt an identity for each of the software repositories they wanted to ...
  • Integrating Open Source Software Repositories on the Web through Linked Data 

    Iqbal, A; Decker S (2015)
    In this paper, we propose a novel approach to the problem of integrating code forges based on metadata (e.g., programming language, database, intended audience, operating system), similar software projects and software ...
  • An Interactive Map of Semantic Web Ontology Usage 

    Kinsella, Sheila; Bojars, Uldis; Harth, Andreas; Breslin, John; Decker, Stefan (IEEE, 2008)
    Publishing information on the Semantic Web using common formats enables data to be linked together, integrated and reused. In order to fully leverage the potential for interlinking data by reusing existing schemas, an ...
  • Investigating Context Parameters in Technology Term Recognition 

    QasemiZadeh, Behrang; Handschuh, siegfried (2014)
    We propose and evaluate the task of technology term recognition: a method to extract technology terms at a synchronic level from a corpus of scientific publications. The proposed method is built on the principles of ...
  • Invited Talk: Can We Deal with Emergent Knowledge Yet? 

    Nováček, Vít (VSE Prague, 2010)
    This overview paper briefly describes problems we need to tackle if we want to meaningfully and efficiently process emergent knowledge. By this term we essentially mean knowledge continually emerging in a bottom-up manner ...
  • IRIS: English-Irish machine translation system 

    Arcan, Mihael; Lane, Caoilfhionn; Ó Droighneáin, Eoin; Buitelaar, Paul (European Language Resources Association, 2016-05-23)
    We describe IRIS, a statistical machine translation (SMT) system for translating from English into Irish and vice versa. Since Irish is considered an under-resourced language with a limited amount of machine-readable text, ...
  • JeromeDL - Adding Semantic Web Technologies to Digital Libraries 

    Kruk, Sebastian Ryszard; Decker, Stefan (Springer, 2005)
    In recent years more and more information has been made available on the Web. High quality information is often stored in dedicated databases of digital libraries, which are on their way to become expanding islands of well ...
  • Kanopy: Analysing the Semantic Network around Document Topics 

    Hulpus, Ioana; Hayes, Conor; Karnstedt, Marcel; Greene, Derek; Jozwowicz, Marek (Springer, 2013)
    External knowledge bases, both generic and domain specific, available on the Web of Data have the potential of enriching the content of text documents with structured information. We present the Kanopy system that makes ...