Sökning: "Ordvektorer"

Visar resultat 1 - 5 av 9 uppsatser innehållade ordet Ordvektorer.

1. 1. Image-Guided Zero-Shot Object Detection in Video Games : Using Images as Prompts for Detection of Unseen 2D Icons

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

   Författare :Axel Larsson; [2023]
   Nyckelord :Computer Vision; Deep learning; Machine learning; Object detection; Zeroshot; Datorseende; Djupinlärning; Maskininlärning; Objektdetektering; Zero-shot;

   Sammanfattning : Object detection deals with localization and classification of objects in images, where the task is to propose bounding boxes and predict their respective classes. Challenges in object detection include large-scale annotated datasets and re-training of models for specific tasks. LÄS MER

3. 2. Fake Mass-Produced Advertisements Detection on Global Online Adult Service Websites

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

   Författare :Ernest Pokropek; [2023]
   Nyckelord :Machine learning; Spam detection; Mass-produced spam; Global adult online services; Maskininlärning; Detektering av Spam; Massproducerad Spam; Globala Webbplatser som Erbjuder Eskorttjänster;

   Sammanfattning : A significant amount of sex trafficking victims are being advertised on online adult services, which are currently being flooded with spam. Investigators rely on online adult services to track cases of sex trafficking; however, the ever-increasing volume of spam poses a mounting challenge, making their task progressively more difficult. LÄS MER

4. 3. Automatic Pronoun Resolution for Swedish

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

   Författare :Camilla Ahlenius; [2020]
   Nyckelord :Pronoun resolution; Mitkov’s algorithm; Support Vector Machine; Supervised learning; SVM-Light-TK; Tree kernels; Dependency trees; Word embeddings; Pronomenbestämning; Mitkovs algoritm; Stödvektormaskin; Övervakad inlärning; SVM-Light-TK; Trädkärnor; Dependensträd; Ordvektorer;

   Sammanfattning : This report describes a quantitative analysis performed to compare two different methods on the task of pronoun resolution for Swedish. The first method, an implementation of Mitkov’s algorithm, is a heuristic-based method — meaning that the resolution is determined by a number of manually engineered rules regarding both syntactic and semantic information. LÄS MER

5. 4. Dynamic Student Embeddings for a Stable Time Dimension in Knowledge Tracing

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

   Författare :Clara Tump; [2020]
   Nyckelord :Knowledge Tracing; Exercise Recommendation; Adaptive Learning; Machine Learning; Word Embeddings; Dynamic Embeddings; Recurrent Neural Networks; Long Short-Term Memory Neural Networks; Kunskapsspårning; Uppgiftsrekommendation; Adaptivt Lärande; Maskininlärning; Ordvektorer; Dynamiska Studentvektorer; Recurrent Neural Networks; Long ShortTerm Memory Neural Networks;

   Sammanfattning : Knowledge tracing is concerned with tracking a student’s knowledge as she/he engages with exercises in an (online) learning platform. A commonly used state-of-theart knowledge tracing model is Deep Knowledge Tracing (DKT) which models the time dimension as a sequence of completed exercises per student by using a Long Short-Term Memory Neural Network (LSTM). LÄS MER

7. 5. Word2vec2syn : Synonymidentifiering med Word2vec

   Kandidat-uppsats, Linköpings universitet/Statistik och maskininlärning

   Författare :Tove Pettersson; [2019]
   Nyckelord :Word2vec; synonym identification; vector space model; word vectors; cosine similarity; Word2vec; synonymidentifiering; vektorrymdsmodell; ordvektorer; cosinuslikhet;

   Sammanfattning : Inom NLP (eng. natural language processing) är synonymidentifiering en av de språkvetenskapliga utmaningarna som många antar. Fodina Language Technology AB är ett företag som skapat ett verktyg, Termograph, ämnad att samla termer inom företag och hålla den interna språkanvändningen konsekvent. LÄS MER