Sökning: "Dense retrieval"

Visar resultat 1 - 5 av 10 uppsatser innehållade orden Dense retrieval.

1. 1. Efficient Utilization of Video Embeddings from Video-Language Models

   Master-uppsats, Linköpings universitet/Datorseende

   Författare :Felix Lindgren; [2023]
   Nyckelord :VLM; CLIP; transformers; machine learning; video retrieval; activitynet; efficient training; aggregation;

   Sammanfattning : In the digital age where video content is abundant, this thesis investigates the efficient adaptation of an existing video-language model (VLM) to new data. The research leverages CLIP, a robust language-vision model, for various video-related tasks including video retrieval. LÄS MER

3. 2. Synthetic data generation for domain adaptation of a retriever-reader Question Answering system for the Telecom domain : Comparing dense embeddings with BM25 for Open Domain Question Answering

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

   Författare :Filip Döringer Kana; [2023]
   Nyckelord :Natural Language Processing; Transformers; Deep Learning; Question Answering; Data Generation; Språkteknologi; Transformers; Djupinlärning; Frågebesvaring; Datagenerering;

   Sammanfattning : Having computer systems capable of answering questions has been a goal within Natural Language Processing research for many years. Machine Learning systems have recently become increasingly proficient at this task with large language models obtaining state-of-the-art performance. LÄS MER

4. 3. 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

5. 4. Trade-offs between Quality and Efficiency in Multilingual Dense Retrieval

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

   Författare :Emma Schüldt; [2022]
   Nyckelord :Dense retrieval; Binary Retrieval; Semantic search; ColBERT; Multilingual; MSMarco; Tät informationssökning; Binär informationssökning; Semantisk sökning; ColBERT; Flerspråkig; MS Marco;

   Sammanfattning : As the amount of content online grows, information retrieval becomes increasingly crucial. Traditional information retrieval does not take the text order into account and is also dependent on exact text matching between the query and the document. LÄS MER

7. 5. The Value of Redesigning Visualization Tools : A case study on carbon emissions data

   Kandidat-uppsats, Linnéuniversitetet/Institutionen för datavetenskap och medieteknik (DM)

   Författare :Louise Jakobsson; [2021]
   Nyckelord :Data visualization; Data visualization tool; Visual Information Seeking Mantra; Design principles; Carbon emissions data;

   Sammanfattning : Organizations can reduce carbon emissions by collecting data on what their emissions are and replace activities that are emission dense. To aid exploration, emission data can be visualized using a data visualization tool. LÄS MER