Essays about: "Text style transfer"

Showing result 1 - 5 of 9 essays containing the words Text style transfer.

  1. 1. Exploring toxic lexicon similarity methods with the DRG framework on the toxic style transfer task

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

    Author : Martin Iglesias; [2023]
    Keywords : Detoxifcation; Text style transfer; Deep learning; Transformers; Linguistics; Natural Language Processing; Hate speech; Text style-conditional generation; Large language model; Avgiftning; Överföring av textstil; Djupinlärning; Transformatorer; Lingvistik; Naturlig språkbehandling; Hatprat; Textstil - villkorlig generering; Stor språkmodell;

    Abstract : The topic of this thesis is the detoxification of language in social networks with a particular focus on style transfer techniques that combine deep learning and linguistic resources. In today’s digital landscape, social networks are rife with communication that can often be toxic, either intentionally or unintentionally. READ MORE

  2. 2. Towards Automatic Generation of Personality-Adapted Speech and Emotions for a Conversational Companion Robot

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

    Author : Alessio Galatolo; [2022]
    Keywords : Personality; Emotions; Human-Robot Interaction; Machine Learning; Large Language Models; Text-style transfer; GPT-3; STRAP; Personlighet; Känslor; Människa-robotinteraktion; Maskininlärning; Stora Språkmodeller; Överföring av text; GPT-3; STRAP;

    Abstract : Previous works in Human-Robot Interaction have demonstrated the positive potential benefit of designing highly anthropomorphic robots. This includes physical appearance but also whether they can express emotions, behave in a congruent manner, etc. READ MORE

  3. 3. Style Transfer Paraphrasing for Consistency Training in Sentiment Classification

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

    Author : Núria Casals; [2021]
    Keywords : Semi-Supervised Learning; Data Augmentation; Sentiment Classification; Neural Paraphrasing; Semi-övervakad inlärning; Data förändring; Sentimentklassificering; Neural parafrasering;

    Abstract : Text data is easy to retrieve but often expensive to classify, which is why labeled textual data is a resource often lacking in quantity. However, the use of labeled data is crucial in supervised tasks such as text classification, but semi-supervised learning algorithms have shown that the use of unlabeled data during training has the potential to improve model performance, even in comparison to a fully supervised setting. READ MORE

  4. 4. Smoothening of Software documentation : comparing a self-made sequence to sequence model to a pre-trained model GPT-2

    University essay from Linköpings universitet/Institutionen för datavetenskap

    Author : Joakim Tao; David Thimrén; [2021]
    Keywords : Text style transfer; authorship style transfer; documentation style;

    Abstract : This thesis was done in collaboration with Ericsson AB with the goal of researching the possibility of creating a machine learning model that can transfer the style of a text into another arbitrary style depending on the data used. This had the purpose of making their technical documentation appear to have been written with one cohesive style for a better reading experience. READ MORE

  5. 5. A Comparative Study of the Quality between Formality Style Transfer of Sentences in Swedish and English, leveraging the BERT model

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

    Author : Maria Lindblad; [2021]
    Keywords : Formality Style Transfer; BERT; Natural Language Generation; Swedish Language Models; GYAFC; Encoder-Decoder Models; Överföring av formalitetsstil; BERT; Generering av naturligt språk; Svenska språkmodeller; GYAFC; Kodnings-avkodningsmodeller;

    Abstract : Formality Style Transfer (FST) is the task of automatically transforming a piece of text from one level of formality to another. Previous research has investigated different methods of performing FST on text in English, but at the time of this project there were to the author’s knowledge no previous studies analysing the quality of FST on text in Swedish. READ MORE