Sökning: "Text input methods"

Visar resultat 1 - 5 av 61 uppsatser innehållade orden Text input methods.

1. 1. Where to Fuse

   Master-uppsats, Lunds universitet/Matematisk statistik

   Författare :Lukas Petersson; [2024]
   Nyckelord :Technology and Engineering;

   Sammanfattning : This thesis investigates fusion techniques in multimodal transformer models, focusing on enhancing the capabilities of large language models in understanding not just text, but also other modalities like images, audio, and sensor data. The study compares late fusion (concatenating modality tokens after separate encoding) and early fusion (concatenating before encoding) techniques, examining their respective advantages and disadvantages. LÄS MER

3. 2. Exploration of using Twitter data to predict Swedish political opinion polls with neural networks

   Master-uppsats, Lunds universitet/Matematisk statistik

   Författare :Alexander Gren; Klara Lundgren; [2023]
   Nyckelord :Mathematics and Statistics;

   Sammanfattning : This thesis aims to explore the possibility of using deep learning techniques to mine opinions on Twitter, with the objective to predict the political opinion distribution in Sweden. Different methods of gathering and annotating training data are evaluated to achieve accurate and reliable predictions. LÄS MER

4. 3. Contextual short-term memory for LLM-based chatbot

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

   Författare :Mikael Lauri Aleksi Törnwall; [2023]
   Nyckelord :Chatbot; Artificial Intelligence; Machine Learning; Language Model; Large Language Model; GPT-3; Natural Language Processing; Text Summarization; Dialogue Summarization; Prompt Design; Prompt Programming; Chatbot; Artificiell Intelligens; Maskininlärning; Språkmodell; Stor Språkmodell; GPT-3; Naturlig Ppråkbehandling; Textsammanfattning; Sammanfattning av Dialog; Design för Inmatningsprompt; Inmatningsprompt Programmering;

   Sammanfattning : The evolution of Language Models (LMs) has enabled building chatbot systems that are capable of human-like dialogues without the need for fine-tuning the chatbot for a specific task. LMs are stateless, which means that a LM-based chatbot does not have a recollection of the past conversation unless it is explicitly included in the input prompt. LÄS MER

5. 4. Ensuring Brand Safety by Using Contextual Text Features: A Study of Text Classification with BERT

   Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

   Författare :Lingqing Song; [2023]
   Nyckelord :;

   Sammanfattning : When advertisements are placed on web pages, the context in which the advertisements are presented is important. For example, manufacturers of kitchen knives may not want their advertisement to appear in a news article about a knife-wielding murderer. LÄS MER

7. 5. Text Normalization for Text-to-Speech

   Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

   Författare :Zhaorui Zhang; [2023]
   Nyckelord :;

   Sammanfattning : Text normalization plays a crucial role in text-to-speech systems by ensuring that the input text is in an appropriate format and consists of standardized words prior to grapheme-to-phoneme conversion for text-to-speech. The aim of this study was to assess the performance of five text normalization systems based on different methods. LÄS MER