Sökning: "historical language models"

Visar resultat 1 - 5 av 19 uppsatser innehållade orden historical language models.

1. 1. A Literature Review of Trends, Attitudes and Multilingual Learning in Research on Cross-Linguistic Influence

   Uppsats för yrkesexamina på grundnivå, Göteborgs universitet / Lärarutbildningsnämnden

   Författare :Malin Bergman; Alma Engström; [2023-11-14]
   Nyckelord :cross-linguistic influence; transfer; multilingualism; third language acquisition; language learning;

   Sammanfattning : This literature review identifies what trends and attitudes can be found and how the multilingual learning process is depicted in research on cross-linguistic influence (CLI) between 2009 and 2023. The aim of this is partly to investigate the changes that have followed the EU’s commitment to reinforce multilingualism and to compare current research with historical findings. LÄS MER

3. 2. IŻ SWÓJ JĘZYK MAJĄ! An exploration of the computational methods for identifying language variation in Polish

   Master-uppsats, Göteborgs universitet / Institutionen för filosofi, lingvistik och vetenskapsteori

   Författare :Maria Irena Szawerna; [2023-06-19]
   Nyckelord :language variation; Polish; diachronic linguistics; part-of-speech tagging; lemmatization; corpus linguistics;

   Sammanfattning : Computational approaches to language variation continue to contribute in a relevant way to various fields, including Natural Language Processing (NLP) and linguistics. Being able to accommodate variation within natural language increases the robustness of NLP models and their usefulness in real-life applications; simultaneously, detecting and describing variation and trends that govern it is one of the main goals of sociolinguistics and historical linguistics, meaning that some of the advances in NLP can contribute to these fields as well. LÄS MER

4. 3. Models, Keys, and Cryptanalysis: Evaluating historical statistical language models in cryptanalysis of homophonic substitution ciphers

   Kandidat-uppsats, Göteborgs universitet/Institutionen för filosofi, lingvistik och vetenskapsteori

   Författare :Filip Fornmark; [2023-01-19]
   Nyckelord :statistical language models; cryptanalysis; historical cryptology; homophonic substitution;

   Sammanfattning : This thesis presents an empirical study connected to historical cryptography and especially within the framework of the research project DECRYPT. One of the research questions in the DECRYPT project relates to the use of language models for automatic cryptanalysis. LÄS MER

5. 4. Air quality prediction in metropolitan areas using deep learning methods

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

   Författare :Augustin Ionut Ionascu; [2023]
   Nyckelord :air quality; forecasting; time-series; univariate; multivariate; multi-step; Attention; Transformer;

   Sammanfattning : The rapid growth of the world's urban population shows that people are increasingly moving to cities. In recent decades, the frequent occurrence of smog caused by increasing industrialization has brought environmental pollution to record highs. LÄS MER

7. 5. Attention based Knowledge Tracing in a language learning setting

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

   Författare :Sebastiaan Vergunst; [2022]
   Nyckelord :Knowledge Tracing; Exercise Recommendation; Personalised Learning; Recurrent Neural Network; Attention; Self-Attention; Exercise Embedding; Kunskapsspårning; Övningsrekommendation; Personligt Anpassad Inlärning; Rekurrenta Neurala Nätverk; Uppmärksamhet; Självuppmärksamhet; Övningsembedding;

   Sammanfattning : Knowledge Tracing aims to predict future performance of users of learning platforms based on historical data, by modeling their knowledge state. In this task, the target is a binary variable representing the correctness of the exercise, where an exercise is a word uttered by the user. LÄS MER