Browsing Theses by Subject "natural language processing"
Now showing items 21-36 of 36
-
Logging Statements Analysis and Automation in Software Systems with Data Mining and Machine Learning Techniques
(University of Waterloo, 2022-01-19)Log files are widely used to record runtime information of software systems, such as the timestamp of an event, the name or ID of the component that generated the log, and parts of the state of a task execution. The rich ... -
Mining Question and Answer Sites for Automatic Comment Generation
(University of Waterloo, 2014-04-29)Code comments improve software maintainability, programming productivity, and software reliability. To address the comment scarcity issue in many projects and save developers’ time in writing comments, we propose a new, ... -
Multilingual Grammatical Error Detection And Its Applications to Prompt-Based Correction
(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
(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
(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
(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 ... -
The Persistence of Involuntary Memory: Analyzing Phenomenology, Links to Mental Health, and Content
(University of Waterloo, 2022-08-23)In daily life, memories of one’s personal past are often retrieved involuntarily (i.e., unintentionally and effortlessly). Termed involuntary autobiographical memories (IAMs), recent evidence suggests that these are often ... -
Prompt-tuning in Controlled Dialogue Generation
(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 ... -
Retrieving Supporting Evidence for Generative Question Answering
(University of Waterloo, 2023-12-18)Current large language models (LLMs) can exhibit near-human levels of performance on many natural language-based tasks, including open-domain question answering. Unfortunately, at this time, they also convincingly hallucinate ... -
Semi-Automated Methods for Measuring Practice Conformance for Capital Projects
(University of Waterloo, 2020-08-06)The goal of this thesis is to explore semi-automated methods for measuring practice conformance for capital projects. Thorough measurement of practice conformance for capital projects typically requires manual audits. ... -
Sentiment Lexicon Induction and Interpretable Multiple-instance Learning in Financial Markets
(University of Waterloo, 2020-09-28)Sentiment analysis has been widely used in the domain of finance. There are two most common textual sentiment analysis methods in finance: \textit{dictionary-based approach} and \textit{machine learning approach}. The ... -
Towards Measuring Coherence in Poem Generation
(University of Waterloo, 2023-01-11)Large language models (LLM) based on transformer architecture and trained on massive corpora have gained prominence as text-generative models in the past few years. Even though large language models are very adept at ... -
Unsupervised Syntactic Structure Induction in Natural Language Processing
(University of Waterloo, 2021-09-07)This work addresses unsupervised chunking as a task for syntactic structure induction, which could help understand the linguistic structures of human languages especially, low-resource languages. In chunking, words of a ... -
Using Natural Language Processing to Detect Breast Cancer Recurrence in Clinical Notes: A Hierarchical Machine Learning Approach
(University of Waterloo, 2021-04-26)The vast amount of data amassed in the electronic health records (EHRs) creates needs and opportunities for automated extraction of information from EHRs using machine learning techniques. Natural language processing (NLP) ... -
Using Rhetorical Figures and Shallow Attributes as a Metric of Intent in Text
(University of Waterloo, 2011-05-20)In this thesis we propose a novel metric of document intent evaluation based on the detection and classification of rhetorical figure. In doing so we dispel the notion that rhetoric lacks the structure and consistency ... -
Virtual Assistant Design for Water Systems Operation
(University of Waterloo, 2020-01-23)Water management systems such as wastewater treatment plants and water distributions systems are big systems which include a multitude of variables and performance indicators that drive the decision making process for ...