Sökning: "embedding models"

Visar resultat 16 - 20 av 106 uppsatser innehållade orden embedding models.

1. 16. Implementation av adaptiv evaluering för feedback i chatbot för yrkessvenska

   Kandidat-uppsats, KTH/Datavetenskap

   Författare :Sandra Persson; Hanna Skorupka; [2022]
   Nyckelord :;

   Sammanfattning : The report aims to study whether the implementation of language models in a chatbot for Swedish can make language learning more effective. A fundamental factor for an individual to have the opportunity to be integrated into the labor market and into society, is language. LÄS MER

3. 17. Distilling Multilingual Transformer Models for Efficient Document Retrieval : Distilling multi-Transformer models with distillation losses involving multi-Transformer interactions

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Xuecong Liu; [2022]
   Nyckelord :Dense Passage Retrieval; Knowledge Distillation; Multilingual Transformer; Document Retrieval; Open Domain Question Answering; Tät textavsnittssökning; kunskapsdestillering; flerspråkiga transformatorer; dokumentsökning; domänlöst frågebesvarande;

   Sammanfattning : Open Domain Question Answering (OpenQA) is a task concerning automatically finding answers to a query from a given set of documents. Language-agnostic OpenQA is an increasingly important research area in the globalised world, where the answers can be in a different language from the question. LÄS MER

4. 18. Integrating Fire Evacuation into the Building Information Modelling Workflow

   Master-uppsats, Lunds universitet/Avdelningen för Brandteknik

   Författare :Nazim Yakhou; [2022]
   Nyckelord :Fire Safety Engineering; Building Information Modelling; Fire Evacuation; Performance Based Design; Golden Thread of Information; Technology and Engineering;

   Sammanfattning : Building Information Modelling (BIM) is arising gradually as a useful methodology in the AEC field. One of the many benefits of BIM is coordination between stakeholders from multiple disciplines. However, the field of Fire Safety Engineering (FSE) is relatively lagging by its lack of integration into this digital workflow. LÄS MER

5. 19. On the use of knowledge graph embeddings for business expansion

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Niklas Rydberg; [2022]
   Nyckelord :Knowledge Graph Embeddings; Knowledge Graphs; Link Prediction; Machine Learning; Artificial Intelligence; Kunskapsgrafinbäddningar; Kunskapsgrafer; Länkförutsägelser; Maskininlärning; Artificiell Intelligens;

   Sammanfattning : The area of Knowledge Graphs has grown significantly during recent time and has found many different applications both in industrial and academic settings. Despite this, many large Knowledge Graphs are in fact incomplete, which leads to the problem of finding the missing facts in the graphs using Link Prediction. LÄS MER

7. 20. Structural Comparison of Data Representations Obtained from Deep Learning Models

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Tommy Wallin; [2022]
   Nyckelord :Representation Learning; Deep learning models; Image Representations.; Representationsinlärning; Djupinlärningsmodeller; Bildrepresentationer;

   Sammanfattning : In representation learning we are interested in how data is represented by different models. Representations from different models are often compared by training a new model on a downstream task using the representations and testing their performance. LÄS MER