Arama Sonuçları

Listeleniyor 1 - 6 / 6
  • Yayın
    Integrating Turkish Wordnet KeNet to Princeton WordNet: The case of one-to-many correspondences
    (Institute of Electrical and Electronics Engineers Inc., 2019-10) Bakay, Özge; Ergelen, Özlem; Yıldız, Olcay Taner
    In this paper, we introduce a novel approach of forming interlingual relations between multilingual wordnets. We have mapped Turkish senses in KeNet with their corresponding senses in Princeton WordNet by drawing one-To-many correspondences. As a result of language-specific properties, one synset in one language is matched with multiple synsets in the other language in some cases. Our method of integrating KeNet into a multilingual network also included mapping the most frequent 5000 senses in English with their equivalent senses in Turkish. What we demonstrate is that one-To-many interlingual correspondances are necessary to include in mappings both from Turkish-To-English and English-To-Turkish. Furthermore, one-To-many mappings give us insights into the semantic relations to be constructed in Turkish, such as hypernymy.
  • Yayın
    English-Turkish parallel semantic annotation of Penn-Treebank
    (Oficyna Wydawnicza Politechniki Wroclawskiej, 2020) Arıcan, Bilge Nas; Bakay, Özge; Avar, Begüm; Yıldız, Olcay Taner; Ergelen, Özlem
    This paper reports our efforts in constructing a sense-labeled English-Turkish parallel corpus using the traditional method of manual tagging. We tagged a pre-built parallel treebank which was translated from the Penn Treebank corpus. This approach allowed us to generate a resource combining syntactic and semantic information. We provide statistics about the corpus itself as well as information regarding its development process.
  • Yayın
    Comparing sense categorization between English propbank and english wordnet
    (Oficyna Wydawnicza Politechniki Wroclawskiej, 2020) Bakay, Özge; Avar, Begüm; Yıldız, Olcay Taner
    Given the fact that verbs play a crucial role in language comprehension, this paper presents a study which compares the verb senses in English PropBank with the ones in English WordNet through manual tagging. After analyzing 1554 senses in 1453 distinct verbs, we have found out that while the majority of the senses in PropBank have their one-to-one correspondents in WordNet, a substantial amount of them are differentiated. Furthermore, by analysing the differences between our manually-tagged and an automatically-tagged resource, we claim that manual tagging can help provide better results in sense annotation.
  • Yayın
    Problems caused by semantic drift in WordNet synset construction
    (Institute of Electrical and Electronics Engineers Inc., 2019-09) Bakay, Özge; Ergelen, Özlem; Yıldız, Olcay Taner
    In this study, we summarize the semantic drift problem that occur in specific synsets of KeNet, a Turkish WordNet, which is caused by mis-merging of semantically-related lexical items, morphological markings and false part of speech (POS) matchings. We present our approach to these problems in order to eliminate the semantic drift. We have re-analyzed the dictionary definitions of the items, placed those that possess different verbal markings into separate synsets, and divided synsets based on the POS of the items in them.
  • Yayın
    Automatic XML schema matching
    (2009) Kılıç, Yasin Ozan; Aydın, Mehmet Nafiz
    As the enterprise systems increasingly use the XML technology in their data presentation, the Enterprise Application Integration is gradually becoming the problem of Xml Schema matching. Different organizations overall need to exchange information which is mainly all in different Xml Schemas and these schemas need to be transformed before an information exchange takes place. Manually transforming different Xml Schemas is a tedious work and this process needs to be done automatically. This is the problem of Automatic Xml Schema Matching. In this paper, an academic literature review will be given on the subject. The article will examine the problems with contemporary solutions while pointing their weaknesses and propose possible solutions to these problems which reduce it to ontological mapping.
  • Yayın
    A mobile agent platform and an example agent application
    (Işık Üniversitesi, 2004-10) Aydın, Elif; Kuru, Selahattin; Işık Üniversitesi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Yüksek Lisans Programı
    Use and adaptation of software agents in a wide variety of applications are highly expected since they are particularly useful in distributed applications involving peer-to-peer processes. They tend to be applied in many areas such as, searching the internet, finding resumes, retrieving and analyzing documents, shopping,auctions,emaillings,distributed control and monitoring and e-commerce. The term 2mobile agent3 was introduced by Telescript, that supports mobility at the programming language level. Many mobile agent systems including enviroments , languages, supporting software and modelling/simulation tools for MAS(Multi Agent System) development followed such as JACK,JADE,ZEUS,DECAF,Voyage, AgentTool, most implemented in Java , which already supports mobile code, but also in scripting languages, such as Tcl/T kor Python. Mobile agents seem suitable for applications, such as electronic commerce , system administration and management(especially network management), and information retrieval. The purpose of this thesis is to introduce and agent platform to develop mobile agents systems by presenting an simole example which includes various kinds of agents.