Sökning: "dictionary learning"
Visar resultat 21 - 25 av 44 uppsatser innehållade orden dictionary learning.
21. Word Segmentation for Classification of Text
Master-uppsats, Uppsala universitet/Institutionen för informationsteknologiSammanfattning : Compounding is a highly productive word-formation process in some languages that is often problematic for natural language processing applications. Word segmentation is the problem of splitting a string of written language into its component words. LÄS MER
22. Low Supervision, Low Corpus size, Low Similarity! Challenges in cross-lingual alignment of word embeddings : An exploration of the limitations of cross-lingual word embedding alignment in truly low resource scenarios
Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologiSammanfattning : Cross-lingual word embeddings are an increasingly important reseource in cross-lingual methods for NLP, particularly for their role in transfer learning and unsupervised machine translation, purportedly opening up the opportunity for NLP applications for low-resource languages. However, most research in this area implicitly expects the availablility of vast monolingual corpora for training embeddings, a scenario which is not realistic for many of the world's languages. LÄS MER
23. Das Wort kenne ich! : Eine Frequenzanalyse von Vokabeln in zwei DaF-Lehrwerken für das Niveau A2
Uppsats för yrkesexamina på avancerad nivå, Linnéuniversitetet/Institutionen för språk (SPR)Sammanfattning : This two-part study investigates the word frequency of a total of 1296 vocabularies presented in the textbooks Digilär Tyska 3 and Lieber Deutsch 3 2.0, which correspond to the language proficiency level A2. LÄS MER
24. Implementation of an 8-bit Dynamic Fixed-Point Convolutional Neural Network for Human Sign Language Recognition on a Xilinx FPGA Board
Master-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknikSammanfattning : The goal of this thesis work is to implement a convolutional neural network on an FPGA device with the capability of recognising human sign language. The set of gestures that the neural network can identify has been taken from the Swedish sign language, and it consists of the signs used for representing the letters of the Swedish alphabet (a.k.a. LÄS MER
25. Drug Name Recognition in Reports on Concomitant Medication
Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen för systemteknikSammanfattning : This thesis evaluates if and how drug name recognition can be used to find drug names in verbatims from reports on concomitant medication in clinical trial studies. In clinical trials, reports on concomitant medication are written if a trial participant takes other drugs than the studied drug. LÄS MER