Essays about: "contrastive language learning"

Showing result 1 - 5 of 22 essays containing the words contrastive language learning.

  1. 1. Leveraging Large Language Models for Firm-Intelligence: A RAG Framework Approach

    University essay from Lunds universitet/Statistiska institutionen

    Author : Niclas Wölner-Hanssen; [2024]
    Keywords : Artificial Intelligence; Large Language Models; Retrieval Augmented Generation; Retrieval Augmented Generation Assessment; Contrastive Learning; Mathematics and Statistics;

    Abstract : In the wake of OpenAI's release of ChatGPT in November 2022, powered by the 175 billion parameter neural network GPT-3, the potential applications of Large Language Models (LLMs) in various sectors have become evident. One such application lies in hedge funds and trading desks where knowledge sharing is paramount. READ MORE

  3. 2. Information Extraction for Test Identification in Repair Reports in the Automotive Domain

    University essay from Uppsala universitet/Institutionen för lingvistik och filologi

    Author : Huang Jie; [2023]
    Keywords : text classification; information retrieval; contrastive learning; prompt-based fine-tuning; large language models;

    Abstract : The knowledge of tests conducted on a problematic vehicle is essential for enhancing the efficiency of mechanics. Therefore, identifying the tests performed in each repair case is of utmost importance. This thesis explores techniques for extracting data from unstructured repair reports to identify component tests. READ MORE

  4. 3. Anomaly Detection with Machine Learning using CLIP in a Video Surveillance Context

    University essay from Linköpings universitet/Datorseende

    Author : Christoffer Gärdin; [2023]
    Keywords : Datorseende; maskininlärning; CLIP; anomalidetektion; videoövervakning;

    Abstract : This thesis explores the application of Contrastive Language-Image Pre-Training (CLIP), a vision-language model, in an automated video surveillance system for anomaly detection. The ability of CLIP to perform zero-shot learning, coupled with its robustness against minor image alterations due to its lack of reliance on pixel-level image analysis, makes it a suitable candidate for this application. READ MORE

  5. 4. Mother Tongue Influence when Learning a Second Language : A Contrastive Analysis of Swedish Gymnasium Students

    University essay from Högskolan i Halmstad/Akademin för lärande, humaniora och samhälle

    Author : Ebba Müller; Stephanie Dahlquist; [2023]
    Keywords : Linguistics; contrastive analysis; mother tongue; influence; interference; errors;

    Abstract : The intended purpose of this essay was to examine student essays to find out if there are any first language interferences in Swedish students’ written English. First language interference has been researched before, which will be presented in the essay, amongst other terms such as translanguaging, acquisition and language transfer, all explained in the theoretical concepts section. READ MORE

  6. 5. Methods for data and user efficient annotation for multi-label topic classification

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Agnieszka Miszkurka; [2022]
    Keywords : Natural Language Processing; Multi-label text classification; Active Learning; Zero-shot learning; Data Augmentation; Data-centric AI; Naturlig språkbehandling; Textklassificering med multipla klasser; Active Learning; Zero-shot learning; Data Augmentation; Datacentrerad AI;

    Abstract : Machine Learning models trained using supervised learning can achieve great results when a sufficient amount of labeled data is used. However, the annotation process is a costly and time-consuming task. There are many methods devised to make the annotation pipeline more user and data efficient. READ MORE