Sökning: "Bert Can"

Visar resultat 16 - 20 av 124 uppsatser innehållade orden Bert Can.

1. 16. Using Bert To Measure Objective Quality Of Rest-Api Specifications : Automated Approach For Quality Measurement

   Kandidat-uppsats, Blekinge Tekniska Högskola/Institutionen för programvaruteknik

   Författare :Fritz Eriksson; Max Åkesson; [2023]
   Nyckelord :API Specification; BERT; Objective quality; Quality attributes; Sailency highlighting;

   Sammanfattning : Each day, the need for as well as the amount of network-based applications grows and with it the implementation of RESTful APIs. For all these APIs there is a need for documentation of the API's behavior, its benefits, how it interacts with other APIs, and its expected result. To solve this; An API specification is constructed. LÄS MER

3. 17. Comparing Different Transformer Models’ Performance for Identifying Toxic Language Online

   Master-uppsats, Stockholms universitet/Institutionen för data- och systemvetenskap

   Författare :Carl Sundelin; [2023]
   Nyckelord :Artificial Intelligence; Machine Learning; Natural Language Processing; Transformers; RoBERTa; DistilBERT; ALBERT; Toxic Language Identification; Social Media;

   Sammanfattning : There is a growing use of the internet and alongside that, there has been an increase in the use of toxic language towards other people that can be harmful to those that it targets. The usefulness of artificial intelligence has exploded in recent years with the development of natural language processing, especially with the use of transformers. LÄS MER

4. 18. 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

5. 19. Help Document Recommendation System

   Master-uppsats, Malmö universitet/Fakulteten för teknik och samhälle (TS)

   Författare :Keerthi Vijay Kumar; Pinky Mary Stanly; [2023]
   Nyckelord :Document similarity; Recommender systems; content-based filtering; collaborative filtering; Term Frequency-Inverse Document Frequency TF-IDF ; Bidirectional Encoder Representation from Transformers BERT ; Non-Negative Matrix Factorisation NMF ; cosine similarity; K-means clustering;

   Sammanfattning : Help documents are important in an organization to use the technology applications licensed from a vendor. Customers and internal employees frequently use and interact with the help documents section to use the applications and know about the new features and developments in them. LÄS MER

7. 20. Annotating Job Titles in Job Ads using Swedish Language Models

   Master-uppsats, Uppsala universitet/Statistiska institutionen

   Författare :Markus Ridhagen; [2023]
   Nyckelord :Natural language processing; NLP; Named-entity recognition; NER; Bidirectional Encoder Representations from Transformers; BERT; Active Learning;

   Sammanfattning : This thesis investigates automated annotation approaches to assist public authorities in Sweden in optimizing resource allocation and gaining valuable insights to enhance the preservation of high-quality welfare. The study uses pre-trained Swedish language models for the named entity recognition (NER) task of finding job titles in job advertisements from The Swedish Public Employment Service, Arbetsförmedlingen. LÄS MER