Essays about: "Translation model"

Showing result 16 - 20 of 189 essays containing the words Translation model.

  1. 16. Text simplification in Swedish using transformer-based neural networks

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

    Author : Samuel Söderberg; [2023]
    Keywords : Machine learning; Natural language processing; Text simplification; Datasets; Maskininlärning; Neurolingvistisk programmering; Textförenkling; Dataset;

    Abstract : Textförenkling innebär modifiering av text så att den blir lättare att läsa genom ersättning av komplexa ord, ändringar av satsstruktur och/eller borttagning av onödig information. Forskning existerar kring textförenkling på svenska, men användandet av neurala nätverk inom området är begränsat. READ MORE

  3. 17. BERTie Bott’s Every Flavor Labels : A Tasty Guide to Developing a Semantic Role Labeling Model for Galician

    University essay from Uppsala universitet/Institutionen för lingvistik och filologi

    Author : Micaella Bruton; [2023]
    Keywords : natural language processing; NLP; Galician; low-resource language; low resource language; semantic role labeling; SRL; mBERT; XLM-R; transfer-learning; transfer learning; Spanish; verbal indexing; procesamento de linguaxe natural; NLP; Galego; lingua de recursos limitados; etiquetado de papeis semánticos; SRL; mBERT; XLM-R; aprendizaxe por transferencia; Español; indexación verbal; språkteknologiska verktyg; NLP; naturlig språkbehandling; galiciska; språk med begränsade resurser; semantisk rollmärkning; SRL; mBERT; XLM-R; överföringsinlärning; spanska; verbal indexering; verbalindexering; procesamiento del lenguaje natural; NLP; Gallego; idioma de bajos recursos; etiquetado de roles semánticos; SRL; mBERT; XLM-R; aprendizaje por transferencia; Español; indexación verbal;

    Abstract : For the vast majority of languages, Natural Language Processing (NLP) tools are either absent entirely, or leave much to be desired in their final performance. Despite having nearly 4 million speakers, one such low-resource language is Galician. READ MORE

  4. 18. Automated Inference of ACSL Contracts for Programs with Heaps

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

    Author : Oskar Söderberg; [2023]
    Keywords : Formal Verification; Contract Inference; Model Checking; Deductive Verification; Theory of Heaps; ACSL; Translation; Formell Verifiering; Kontrakth¨arledning; Modellprovning; Deduktiv Verifiering; Theory of Heaps; ACSL; Overs¨attning;

    Abstract : Contract inference consists in automatically computing contracts that formally describe the behaviour of program functions. Contracts are used in deductive verification, which is a method for verifying whether a system behaves according to a provided specification. The Saida plugin in Frama-C is a contract inference tool for C code. READ MORE

  5. 19. Stuck in translation: Why public agencies seldom succeed implementing performance budgeting : A case study on output controls of the Swedish Armed Forces

    University essay from Stockholms universitet/Företagsekonomiska institutionen

    Author : Andreas Egevad; [2023]
    Keywords : management accounting; public sector agencies; performance budgeting; efficiency; multiple institutional logics; sociology of translation; trust;

    Abstract : Despite its benefits, output controls are less prevalent than its counterpart input controls in public sector agencies. Performance budgeting aligns the input of resources with the output of products and services systematically, enabling assessment of the efficiency and effectiveness of organizational activities. READ MORE

  6. 20. Through the Blur with Deep Learning : A Comparative Study Assessing Robustness in Visual Odometry Techniques

    University essay from Uppsala universitet/Avdelningen för systemteknik

    Author : Alexander Berglund; [2023]
    Keywords : artificial intelligence; AI; machine learning; ML; deep learning; DL; computer vision; neural networks; NN; convolutional neural networks; CNN; visual odometry; VO; robustness; motion blur; AirForestry; localization; navigation; ego-motion; pose estimation; SLAM; DF-VO; DytanVO; ORB-SLAM3; artificiell intelligens; maskininlärning; datorseende;

    Abstract : In this thesis, the robustness of deep learning techniques in the field of visual odometry is investigated, with a specific focus on the impact of motion blur. A comparative study is conducted, evaluating the performance of state-of-the-art deep convolutional neural network methods, namely DF-VO and DytanVO, against ORB-SLAM3, a well-established non-deep-learning technique for visual simultaneous localization and mapping. READ MORE