Sökning: "word embedding"
Visar resultat 1 - 5 av 8 avhandlingar innehållade orden word embedding.
1. Principal Word Vectors
Sammanfattning : Word embedding is a technique for associating the words of a language with real-valued vectors, enabling us to use algebraic methods to reason about their semantic and grammatical properties. This thesis introduces a word embedding method called principal word embedding, which makes use of principal component analysis (PCA) to train a set of word embeddings for words of a language. LÄS MER
2. Splitting rocks: Learning word sense representations from corpora and lexica
Sammanfattning : The representation of written language semantics is a central problem of language technology and a crucial component of many natural language processing applications, from part-of-speech tagging to text summarization. These representations of linguistic units, such as words or sentences, allow computer applications that work with language to process and manipulate the meaning of text. LÄS MER
3. Le titre de presse : Analyses syntaxique, pragmatique et rhétorique
Sammanfattning : What are the linguistic characteristics of French newspapers headlines? Employing three aspects of linguistic analysis (syntax, pragmatics and stylistics), the present thesis describes and analyses the textual "genre" of the headline. The author regards a newspaper headline as an autonomous text which carries various functions within the newspaper's discourse and therefore has specific features as regards language use. LÄS MER
4. Tillvaratagna effekter. Om Jan Håfströms konstnärskap och konstnärsroll
Sammanfattning : In this thesis the oeuvre of the Swedish artist Jan Håfström (born 1937), from his debut in 1966 until 2002, is presented for the first time in a comprehensive approach. Concepts linked to modernism and postmodernism are used as a frame and the art works are discussed in a comparative way, placing the artist in an international context. LÄS MER
5. Quantifying Meaning
Sammanfattning : Distributionella semantikmodeller är en klass av maskininlärningsmodeller med syfte att konstruera representationer som fångar semantik, i.e. mening, av objekt som bär mening på ett datadrivet sätt. LÄS MER