Now showing items 1-20 of 24

    • AfriBERTa: Towards Viable Multilingual Language Models for Low-resource Languages 

      Ogueji, Kelechi (University of Waterloo, 2022-08-29)
      There are over 7000 languages spoken on earth, but many of these languages suffer from a dearth of natural language processing (NLP) tools. Multilingual pretrained language models have been introduced to help alleviate ...
    • Controlled Generation of Stylized Text Using Semantic and Phonetic Representations 

      Gudmundsson, Egill Ian (University of Waterloo, 2022-01-21)
      Neural networks are a popular choice of models for the purpose of text generation. Variational autoencoders have been shown to be good at reconstructing text and generating novel text. However, controlling certain aspects ...
    • Cross-Domain Sentence Modeling for Relevance Transfer with BERT 

      Akkalyoncu Yilmaz, Zeynep (University of Waterloo, 2019-12-16)
      Standard bag-of-words term-matching techniques in document retrieval fail to exploit rich semantic information embedded in the document texts. One promising recent trend in facilitating context-aware semantic matching has ...
    • Disentanglement of Syntactic Components for Text Generation 

      Das, Utsav Tushar (University of Waterloo, 2022-02-18)
      Modelling human generated text, i.e., natural language data, is an important challenge in artificial intelligence. A good AI program should be able to understand and analyze natural language, and generate fluent and accurate ...
    • Emotion-Aware and Human-Like Autonomous Agents 

      Asghar, Nabiha (University of Waterloo, 2019-12-20)
      In human-computer interaction (HCI), one of the technological goals is to build human-like artificial agents that can think, decide and behave like humans during the interaction. A prime example is a dialogue system, where ...
    • An Experimental Analysis of Multi-Perspective Convolutional Neural Networks 

      Tu, Zhucheng (University of Waterloo, 2018-05-16)
      Modelling the similarity of sentence pairs is an important problem in natural language processing and information retrieval, with applications in tasks such as paraphrase identification and answer selection in question ...
    • Extracting Non-Functional Requirements from Unstructured Text 

      Ezami, Sahba (University of Waterloo, 2018-01-18)
      Non-functional requirements (NFRs) of a software system describe desired quality attributes rather than specific user-visible features; NFRs model stakeholder expectations about pervasive system properties such as performance, ...
    • Facilitating Information Access for Heterogeneous Data Across Many Languages 

      Shi, Peng (University of Waterloo, 2023-01-25)
      Information access, which enables people to identify, retrieve, and use information freely and effectively, has attracted interest from academia and industry. Systems for document retrieval and question answering have ...
    • From Atoms to the Solar System: Generating Lexical Analogies from Text 

      Chiu, Pei-Wen Andy (University of Waterloo, 2006)
      A <em>lexical analogy</em> is two pairs of words (<em>w</em><sub>1</sub>, <em>w</em><sub>2</sub>) and (<em>w</em><sub>3</sub>, <em>w</em><sub>4</sub>) such that the relation between <em>w</em><sub>1</sub> and <em>w</em>< ...
    • Future Sight: Dynamic Story Generation with Large Pretrained Language Models 

      Zimmerman, Brian (University of Waterloo, 2022-08-23)
      Automated story generation has been an open problem in computing for many decades. Only with the recent wave of deep learning research have neural networks been applied to automated story generation tasks. Current deep ...
    • GRS: Combining Generation and Revision in Unsupervised Sentence Simplification 

      Dehghan, Mohammad (University of Waterloo, 2022-08-30)
      Text simplification is a task in the natural language processing field that alters a given text to reduce the structural and lexical complexity of the text while preserving the underlying meaning. We can classify existing ...
    • 'Healthy' Coreference: Applying Coreference Resolution to the Health Education Domain 

      Hirtle, David Z. (University of Waterloo, 2008-08-26)
      This thesis investigates coreference and its resolution within the domain of health education. Coreference is the relationship between two linguistic expressions that refer to the same real-world entity, and resolution ...
    • Innovations in Domain Knowledge Augmentation of Contextual Models 

      Michalopoulos, Georgios (University of Waterloo, 2022-08-03)
      The digital transformation of our society is creating a tremendous amount of data at an unprecedented rate. A large part of this data is in unstructured text format. While enjoying the benefit of instantaneous data access, ...
    • An Investigation of Word Sense Disambiguation for Improving Lexical Chaining 

      Enss, Matthew (University of Waterloo, 2006)
      This thesis investigates how word sense disambiguation affects lexical chains, as well as proposing an improved model for lexical chaining in which word sense disambiguation is performed prior to lexical chaining. A ...
    • KG-Pipeline: An Automated Knowledge Graph Generation Framework 

      Vezvaei, Alireza (University of Waterloo, 2022-09-16)
      Knowledge Graphs (KGs) have many applications, specifically in information retrieval and question answering. Community projects are conducted for building large-scale KGs with crowdsourcing, but building KGs with this ...
    • Multilingual Grammatical Error Detection And Its Applications to Prompt-Based Correction 

      Sutter Pessurno de Carvalho, Gustavo (University of Waterloo, 2024-01-05)
      Grammatical Error Correction (GEC) and Grammatical Error Correction (GED) are two important tasks in the study of writing assistant technologies. Given an input sentence, the former aims to output a corrected version of ...
    • Neural Text Generation from Structured and Unstructured Data 

      Shahidi, Hamidreza (University of Waterloo, 2019-08-28)
      A number of researchers have recently questioned the necessity of increasingly complex neural network (NN) architectures. In particular, several recent papers have shown that simpler, properly tuned models are at least ...
    • Novel Methods for Natural Language Modeling and Pretraining 

      Bai, He (University of Waterloo, 2023-02-21)
      This thesis is about modeling language sequences to achieve lower perplexity, better generation, and benefit downstream language tasks; specifically, this thesis addresses the importance of natural language features including ...
    • Parlez-vous le hate?: Examining topics and hate speech in the alternative social network Parler 

      Ward, Ethan (University of Waterloo, 2021-12-23)
      Over the past several years, many “alternative” social networks have sprung up, with an emphasis on minimal moderation and protection of free speech. Although they claim to be politically neutral, they have been a haven ...
    • Prompt-tuning in Controlled Dialogue Generation 

      Liu, Runcheng (University of Waterloo, 2022-12-22)
      Recent years have witnessed a prosperous development of dialogue response generation since the advent of Transformer. Fine-tuning pretrained language models for different downstream tasks has become the dominant paradigm ...

      UWSpace

      University of Waterloo Library
      200 University Avenue West
      Waterloo, Ontario, Canada N2L 3G1
      519 888 4883

      All items in UWSpace are protected by copyright, with all rights reserved.

      DSpace software

      Service outages