Sökning: "Shallow Parsing"

Hittade 3 uppsatser innehållade orden Shallow Parsing.

  1. 1. Syntactic Crossroads: Testing L2 sensitivity to Strong Crossover in an online experiment.

    Master-uppsats, Stockholms universitet/Institutionen för svenska och flerspråkighet

    Författare :Daniele Tucciarone; [2022]
    Nyckelord :;

    Sammanfattning : We investigated sensitivity of non-native speakers of English to the Strong Crossover (SCO) constraint and Binding Principle C. Taking Clahsen & Felser’s (2006) Shallow Structure Hypothesis as a theoretical foundation, we tested whether non-native speakers would show a similar ability in predictively processing syntactic gaps in Strong Crossover configurations as had English native speakers in Kush et al. LÄS MER

  3. 2. Word Representations and Machine Learning Models for Implicit Sense Classification in Shallow Discourse Parsing

    Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

    Författare :Jimmy Callin; [2017]
    Nyckelord :machine learning; neural networks; word representations; word embeddings; distributional semantic models; word vectors; discourse parsing; shallow discourse parsing; maskininlärning; neurala nätverk; ordrepresentationer; distributionella semantiska modeller; diskursparsning;

    Sammanfattning : CoNLL 2015 featured a shared task on shallow discourse parsing. In 2016, the efforts continued with an increasing focus on sense classification. In the case of implicit sense classification, there was an interesting mix of traditional and modern machine learning classifiers using word representation models. LÄS MER

  4. 3. A comparative study of structured prediction methods for sequence labeling

    Kandidat-uppsats, KTH/Skolan för datavetenskap och kommunikation (CSC)

    Författare :Aitor Palacios Cuesta; [2016]
    Nyckelord :;

    Sammanfattning : Some machine learning tasks have a complex output, rather than a real number or a class. Those outputs are composed by elements which have interdependences and structural properties. Methods which take into account the form of the output are known as structured prediction techniques. LÄS MER