Avancerad sökning

Visar resultat 1 - 5 av 148 avhandlingar som matchar ovanstående sökkriterier.

1. 1. Principal Word Vectors

   Författare :Ali Basirat; Joakim Nivre; Hinrich Schütze; Uppsala universitet; []
   Nyckelord :HUMANIORA; HUMANITIES; NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; word; context; word embedding; principal component analysis; PCA; sparse matrix; singular value decomposition; SVD; entropy;

   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

3. 2. Learning based Word Search and Visualisation for Historical Manuscript Images

   Författare :Tomas Wilkinson; Anders Brun; Josep Lladós; Uppsala universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; Word Spotting; Convolutional Neural Networks; Deep Learning; Region Proposals; Historical Manuscripts; Computer Vision; Image Analysis; Visualisation; Document Analysis; Computerized Image Processing; Datoriserad bildbehandling;

   Sammanfattning : Today, work with historical manuscripts is nearly exclusively done manually, by researchers in the humanities as well as laypeople mapping out their personal genealogy. This is a highly time consuming endeavour as it is not uncommon to spend months with the same volume of a few hundred pages. LÄS MER

4. 3. Document Image Processing for Handwritten Text Recognition : Deep Learning-based Transliteration of Astrid Lindgren’s Stenographic Manuscripts

   Författare :Raphaela Heil; Anders Hast; Ekta Vats; Fredrik Wahlberg; Andreas Fischer; Uppsala universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; document image processing; handwritten text recognition; stenography; strikethrough; Computerized Image Processing; Datoriserad bildbehandling;

   Sammanfattning : Document image processing and handwritten text recognition have been applied to a variety of materials, scripts, and languages, both modern and historic. They are crucial building blocks in the on-going digitisation efforts of archives, where they aid in preserving archival materials and foster knowledge sharing. LÄS MER

5. 4. Bayesian Models for Multilingual Word Alignment

   Författare :Robert Östling; Mats Wirén; Ola Knutsson; Jörg Tiedemann; Sharon Goldwater; Stockholms universitet; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; word alignment; parallel text; Bayesian models; MCMC; linguistic typology; sign language; annotation transfer; transfer learning; Linguistics; lingvistik;

   Sammanfattning : In this thesis I explore Bayesian models for word alignment, how they can be improved through joint annotation transfer, and how they can be extended to parallel texts in more than two languages. In addition to these general methodological developments, I apply the algorithms to problems from sign language research and linguistic typology. LÄS MER

7. 5. De sammansatta ordens accentuering i Skånemålen

   Författare :Mathias Strandberg; Staffan Fridell; Tomas Riad; Lars-Olof Delsing; Uppsala universitet; []
   Nyckelord :HUMANIORA; HUMANITIES; tonal word accent; tone accent; word accent; accent 1; accent 2; stress; second-element stress; compounds; compound words; Scanian; dialects; Swedish; etymology; syncope; loanwords; borrowing; ordaccent; tonaccent; accent 1; accent 2; betoning; efterledsbetoning; sammansättningar; sammansatta ord; skånska; dialekter; svenska; etymologi; synkope; lånord; Nordiska språk; Scandinavian Languages;

   Sammanfattning : Swedish has a contrast between two so-called tonal word accents: accent 1 and accent 2. In central standard Swedish, for example, compound words generally have accent 2 and primary stress on the first element. LÄS MER