Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 6 of 6 for “"Text Style Transfer"”.

  1. Empathetic Text Style Transfer Layer for Conversational Agents a modular architecture and new resource for the italian language

    … a modular framework based on an Empathetic Text Style Transfer. This architectural paradigm decouples the generation of empathetic expression from the underlying dialogic and domain‐expert components, enabling the enhancement of pre‐existing conversational agent infrastructures without …

    trento Repository record for Empathetic Text Style Transfer Layer for Conversational Agents a modular architecture and new resource for the italian language (opens in a new tab)

  2. Deep Generative Models for Natural Language Generation

    … generative adversarial network for generating texts. We first examine limitations of the commonly used Generative Adversarial Networks (GANs) on text generation tasks, and propose a novel ranking-based generative adversarial network, RankGAN, for generating high-quality language descriptions. …

    washington Repository record for Deep Generative Models for Natural Language Generation (opens in a new tab)

  3. Representation learning of natural language and its application to language understanding and generation

    … integrate intensive information such as contextualized features from unlabeled text corpora. In this dissertation, we continue this line of research to incorporate rich knowledge into generic embeddings. We show that word representation could be enriched with various information including …

    uiuc Repository record for Representation learning of natural language and its application to language understanding and generation (opens in a new tab)

  4. Exploring Advanced Techniques for Better Generative Modeling

    … Bayesian sampling, image or video generation and text generation. DGMs are typically learned to approximate complex and high-dimensional distributions, and then to generate samples that reside in the distributions. Although last decades have seen rapid development in understanding and designing …

    buffalo Repository record for Exploring Advanced Techniques for Better Generative Modeling (opens in a new tab)

  5. Investigating Conversational Access to Historical Content

    … agent, comprising three stages: retrieval, contextualization, and style transfer. Rather than building a full end-to-end system, the dissertation begins with an investigation into each component individually. First, foundational techniques for conversational search are developed through …

    maryland Repository record for Investigating Conversational Access to Historical Content (opens in a new tab)

  6. Defending Against Trojan Attacks on Neural Network-based Language Models

    … patch of pixel values added to the images and in text domain, it can be a set of words. In this thesis, we propose Trojan-Miner (T-Miner), a defense scheme against such backdoor attacks on text classification deep learning models. The goal of T-Miner is to detect whether a given classifier is a …

    vt Repository record for Defending Against Trojan Attacks on Neural Network-based Language Models (opens in a new tab)