Sökning: "Beáta Megyesi"

Hittade 3 avhandlingar innehållade orden Beáta Megyesi.

  1. 1. Data-driven syntactic analysis

    Författare :Beata Megyesi; KTH; []
    Nyckelord :natural language processing; machine learning; data-driven methods; part-of-speech tagging; chunking; shallow parsing; evaluation; hidden Markov modeling; maximum entropy learning; memory-based learning; transformation-based learning; morphology; syn;

    Sammanfattning : .... LÄS MER

  3. 2. Spelling Normalisation and Linguistic Analysis of Historical Text for Information Extraction

    Författare :Eva Pettersson; Joakim Nivre; Beáta Megyesi; Michael Piotrowski; Uppsala universitet; []
    Nyckelord :NLP for historical text; spelling normalisation; digital humanities; information extraction; character-based statistical machine translation; SMT; Levenshtein edit distance; language technology; computational linguistics; Computational Linguistics; Datorlingvistik;

    Sammanfattning : Historical text constitutes a rich source of information for historians and other researchers in humanities. Many texts are however not available in an electronic format, and even if they are, there is a lack of NLP tools designed to handle historical text. LÄS MER

  4. 3. From Disorder to Order : Extracting clinical findings from unstructured text

    Författare :Maria Skeppstedt; Hercules Dalianis; Gunnar Nilsson; Beáta Megyesi; Stockholms universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Text mining; named entity recognition; clinical language processing; Computer and Systems Sciences; data- och systemvetenskap;

    Sammanfattning : Medical disorders and findings are examples of important information in health record text. Through developing methods for automatically extracting these entities from the health record text, the possibility of making use of the information by automatic computerised processes increases. LÄS MER