Sökning: "Markus Bergkvist"

Hittade 3 uppsatser innehållade orden Markus Bergkvist.

  1. 1. Surmize: An Online NLP System for Close-Domain Question-Answering and Summarization

    Kandidat-uppsats, Uppsala universitet/Institutionen för informationsteknologi

    Författare :Alexander Bergkvist; Nils Hedberg; Sebastian Rollino; Markus Sagen; [2020]
    Nyckelord :Summary; Summarization; Abstractive Summarization; Extractive Summarization; ASUS; ESUS; Question Answering; Question-Answering; QA; QA Model; QA System; Natural Language Processing; NLP; Online NLP System; Machine Learning; ML; Deep Learning; DL; Close-Domain Question Answering; cdQA; Transformer Model; transformer; Transformer; BERT; Watson; Online QA; Online Summary; Online Summarization; Spacy; FastAPI; Surmize; Huggingface;

    Sammanfattning : The amount of data available and consumed by people globally is growing. To reduce mental fatigue and increase the general ability to gain insight into complex texts or documents, we have developed an application to aid in this task. LÄS MER

  3. 2. Fighting the unwanted customer - An exploratory study of the new controversial brand protection tools

    Magister-uppsats, Lunds universitet/Företagsekonomiska institutionen

    Författare :Niklas De Goys De Mezeyrac; Markus Bergkvist; [2012]
    Nyckelord :Targeting; Segmentation; Celebrity Endorsement; Brand Protection; Unwanted Customers; Business and Economics;

    Sammanfattning : .... LÄS MER

  4. 3. Machine learning in simulated RoboCup

    Magister-uppsats, Blekinge Tekniska Högskola/Institutionen för programvaruteknik och datavetenskap

    Författare :Markus Bergkvist; Tobias Olandersson; [2003]
    Nyckelord :Self-learning; Parameter optimization; Simulated RoboCup; Multi- Agent system; Electric Field Approach;

    Sammanfattning : An implementation of the Electric Field Approach applied to the simulated RoboCup is presented, together with a demonstration of a learning system. Results are presented from the optimization of the Electric Field parameters in a limited situation, using the learning system. LÄS MER