Sökning: "n-gram"

Hittade 5 avhandlingar innehållade ordet n-gram.

  1. 1. Classification of Potentially Unwanted Programs Using Supervised Learning

    Författare :Raja Muhammad Khurram Shahzad; Blekinge Tekniska Högskola; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES;

    Sammanfattning : Malicious software authors have shifted their focus from illegal and clearly malicious software to potentially unwanted programs (PUPs) to earn revenue. PUPs blur the border between legitimate and illegitimate programs and thus fall into a grey zone. LÄS MER

  3. 2. Computational Terminology : Exploring Bilingual and Monolingual Term Extraction

    Författare :Jody Foo; Magnus Merkel; Lars Ahrenberg; Dimitrios Kokkinakis; Linköpings universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; terminology; automatic term extraction; automatic term recognition; computational terminology; terminology management;

    Sammanfattning : Terminologies are becoming more important to modern day society as technology and science continue to grow at an accelerating rate in a globalized environment. Agreeing upon which terms should be used to represent which concepts and how those terms should be translated into different languages is important if we wish to be able to communicate with as little confusion and misunderstandings as possible. LÄS MER

  4. 3. Resources and Applications for Dialectal Arabic: the Case of Levantine

    Författare :Chatrine (kathrein) Qwaider (abu kwaik); Göteborgs universitet; []
    Nyckelord :HUMANIORA; HUMANITIES; NATURVETENSKAP; NATURAL SCIENCES; Dialectal Arabic Natural Language Processing; Computational Linguistics; Dialect Identification; Sentiment Analysis; Machine Learning; Deep Learning; Language modelling; Natural Language processing;

    Sammanfattning : This is a thesis about the computational study of Dialectal Arabic (DA). In particular, the thesis studies DA, with a special emphasis on Levantine Arabic, and develops tools and resources for the computational study of Dialectal Arabic Natural Language Processing (DANLP). LÄS MER

  5. 4. Detecting Rhetorical Figures Based on Repetition of Words: Chiasmus, Epanaphora, Epiphora

    Författare :Marie Dubremetz; Nivre Joakim; Dahllöf Mats; Marcel Cori; Graeme Hirst; Uppsala universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; digital humanities; figure of speech; rhetorical device; machine learning; annotation; Computational Linguistics; Datorlingvistik;

    Sammanfattning : This thesis deals with the detection of three rhetorical figures based on repetition of words: chiasmus (“Fair is foul, and foul is fair.”), epanaphora (“Poor old European Commission! Poor old European Council.”) and epiphora (“This house is mine. This car is mine. LÄS MER

  7. 5. Discourse in Statistical Machine Translation

    Författare :Christian Hardmeier; Joakim Nivre; Jörg Tiedemann; Marcello Federico; Lluís Màrquez; Uppsala universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Statistical machine translation; Discourse-level machine translation; Document decoding; Local search; Pronominal anaphora; Pronoun translation; Neural networks; Computational Linguistics; Datorlingvistik;

    Sammanfattning : This thesis addresses the technical and linguistic aspects of discourse-level processing in phrase-based statistical machine translation (SMT). Connected texts can have complex text-level linguistic dependencies across sentences that must be preserved in translation. However, the models and algorithms of SMT are pervaded by locality assumptions. LÄS MER