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 20 of 48 for “"Text generation"”.

  1. Contrastive Text Generation

    … of law and medicine. Building on a traditional generation pipeline of planning and realization, I propose models for three scenarios with contradictions where the planners identify pertinent pieces of information and consensus to adequately realize relations between them. First, I tackle …

    mit Repository record for Contrastive Text Generation (opens in a new tab)

  2. Context-aware data-to-text generation.

    Data-to-Text Generation (D2T) is the subfield of Artificial Intelligence (AI) and Natural Language Processing (NLP) that aims to build systems capable of summarising nonlinguistic structured data into textual reports. D2T systems extract important insights from domain specific, mostly numerical, …

    rgu Repository record for Context-aware data-to-text generation. (opens in a new tab)

  3. Text Generation and Evaluation for Human-Machine Collaborative Writing

    Natural language generation (NLG) models' ability to generate long, fluent texts has enabled progress across many NLG subfields and increased the types of contributions models can make to human-machine collaborative writing tasks. However, the improved quality of generated text also poses …

    washington Repository record for Text Generation and Evaluation for Human-Machine Collaborative Writing (opens in a new tab)

  4. Learning meaning representations for text generation with deep generative models

    This thesis explores conditioning a language generation model with auxiliary variables. By doing so, we hope to be able to better control the output of the language generator. We explore several kinds of auxiliary variables in this thesis, from unstructured continuous, to discrete, to structured …

    cambridge Repository record for Learning meaning representations for text generation with deep generative models (opens in a new tab)

  5. Responsible Computational Text Generation: AI Content Classification and Policy Framework

    … AI, particularly in producing human-like text, have blurred the lines between human and AI authorship. Since these AI tools rely on stochastic generation rather than traditional scientific reasoning, concerns about misinformation and reliability have emerged, highlighting the need for AI …

    mit Repository record for Responsible Computational Text Generation: AI Content Classification and Policy Framework (opens in a new tab)

  6. Teaching and learning writing at primary school: an exploration of writing environments, transcription and text generation

    … on transcription and its relationship with text-generation in different classroom writing environments (i.e. whether content is teacherdetermined, child-determined, or generated jointly by teachers and children). Method: Nine Year 5 teachers were interviewed about their classroom practice, …

    oxford-brookes Repository record for Teaching and learning writing at primary school: an exploration of writing environments, transcription and text generation (opens in a new tab)

  7. Controllable Language Generation Using Deep Learning

    … and question the capabilities of these models. Text generation, a crucial part of NLP, remains an area where our comprehension is limited while being critical in research.</p> <p>This dissertation focuses on the challenging problem of controlling the general behaviors of language models such as …

    denver Repository record for Controllable Language Generation Using Deep Learning (opens in a new tab)

  8. Framing in Argument Analysis & Generation. Detecting and generating perspectives

    … the majority”. However, detecting the farming in texts and opening a debate is not trivial due to a level of latency in that task. Expressing a frame can be done by a bandwidth of words, naming for certain groups, or even more indirectly by concealing other valid viewpoints of problems or …

    bielefeld Repository record for Framing in Argument Analysis & Generation. Detecting and generating perspectives (opens in a new tab)

  9. Subword segmental neural language generation for Nguni languages

    Deep learning models for text generation are now able to produce fluent and coherent text in many conversational settings. However, such models require large training datasets and are primarily designed for a limited number of high-resource languages. These advances are not directly applicable to …

    cape-town Repository record for Subword segmental neural language generation for Nguni languages (opens in a new tab)

  10. Discrete Diffusion for Text Infilling

    Generative modeling of text is a fundamental challenge in natural language processing. While autoregressive models have achieved remarkable success, they face limitations in parallelizability and flexible control. Discrete diffusion models offer a promising alternative paradigm, leveraging …

    vt Repository record for Discrete Diffusion for Text Infilling (opens in a new tab)

  11. Idiomatic sentence generation and paraphrasing

    … in the neck” for NLP systems. Despite this, text generation tasks related to IEs remain largely under-explored. In this study, we propose two new tasks of idiomatic sentence generation and paraphrasing to fill this research gap. We introduce a curated dataset of 823 IEs, and a parallel corpus …

    uiuc Repository record for Idiomatic sentence generation and paraphrasing (opens in a new tab)

  12. Towards a Strong, Human-Compatible Codenames AI Agent

    … natural language interactions, language generation in multi-agent contexts involving multiple users, imperfect information, and partially misaligned objectives remains extremely challenging. We aim to build search procedures that will enable language models to assist with interactive, …

    mit Repository record for Towards a Strong, Human-Compatible Codenames AI Agent (opens in a new tab)

  13. Influence mining from unstructured big data

    … Models for both Information Thirst and Content Generation, sequentially, in this thesis. To the best of my knowledge, Influence models for Information Thirst and Content Generation have not been studied before. The thesis starts with the introduction of a new data mining problem, i.e., how to …

    uiuc Repository record for Influence mining from unstructured big data (opens in a new tab)

  14. Statistical Learning for Sequential Unstructured Data

    … be organized into predefined structures, such as texts, human behavior status, and system logs, often presented in a sequential format with inherent dependencies. Probabilistic model are commonly used to capture these dependencies in the data generation process through latent parameters and can …

    vt Repository record for Statistical Learning for Sequential Unstructured Data (opens in a new tab)

  15. Designing an Investment Research System for Asset Management Based on Natural Language Processing

    … facilitates automatic processing, analysis, and text generation to specific tasks, aiding investment institutions in swiftly assimilating and dissecting massive volumes of information, and consequently formulating investment research results. NLP can assist investment institutions in rapidly …

    mit Repository record for Designing an Investment Research System for Asset Management Based on Natural Language Processing (opens in a new tab)

  16. Planning multisentential English text using communicative acts

    … content as coherent and cohesive English text. With the goal of identifying generic explanation presentation strategies, a wide range of naturally occurring texts were analyzed with respect to their communicative sttucture, function, content and intended effects on the reader. This …

    cambridge Repository record for Planning multisentential English text using communicative acts (opens in a new tab)

Page 1 of 3