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 18 of 18 for “"Natural Language Inference (NLI)"”.
-
A Psychometric Analysis of Natural Language Inference Using Transformer Language Models
Large language models (LLMs) are poised to transform both academia and industry. But the excitement around these generative AIs has also been met with concern for the true extent of their capabilities. This dissertation helps to address these questions by examining the capabilities of LLMs using …
-
HALLUCINATION OR FACT: PERCEIVED VERACITY OF LARGE LANGUAGE MODELS
The rapid advancement of large language models (LLMs) like OpenAI’s ChatGPT, Google Gemini, and Anthropic’s Claude has positioned them as powerful tools for information synthesis, decision support, and natural language processing in both commercial and defense applications. Despite their fluency …
-
Methods and Challenges In Inference Across Textual Sources
… us. The goal of this dissertation is to develop natural language processing (NLP) techniques to facilitate effective, efficient comparison and validation of information across multiple sources. In NLP, The problem of comparing information across sources closely resembles the task of natural …
-
Producing synthetic instances for textual classification and natural language inference
Natural Language Inference (NLI) is a special type of text classification focused on deduction – a model is presented to a pair of sentences (premise and hypothesis) and classifies the relationship between their meanings. Training models with NLI datasets is key for semantic systems. NLI datasets …
-
Producing synthetic instances for textual classification and natural language inference
Natural Language Inference (NLI) is a special type of text classification focused on deduction – a model is presented to a pair of sentences (premise and hypothesis) and classifies the relationship between their meanings. Training models with NLI datasets is key for semantic systems. NLI datasets …
-
Bridging the Data Gap: LLM-Driven Synthetic Data Generation for Low-Resource Natural Language Inference
… the challenge of data scarcity in low-resource languages by leveraging the dual role of Large Language Models (LLMs) to both generate and annotate data. We evaluate the reliability of LLM-based annotations and examine the effectiveness of LLM-generated synthetic data in improving downstream task …
-
Using Natural Language Processing to Support Software Security Requirement Development
The advent of Natural Language Processing (NLP) tools has had profound effects upon the software requirements engineering process. Engineering requirements are a key part of software development, guiding the overall process and ensuring that the resulting software can properly accomplish the …
-
Introducing controlled reasoning into autoregressive large language models
… text generation process of autoregressive large language models (LLMs), in particular those with a generative pre-trained transformer (GPT) architecture which we categorize into GPT and InstructGPT model types. In both cases, our proposed methods attempt to replicate human cognitive behavior and …
-
SYMBOLIC AND NEURAL APPROACHES TO NATURAL LANGUAGE INFERENCE
Natural Language Inference (NLI) is the task of predicting whether a hypothesis text is entailed (or can be inferred) from a given premise. For example, given the premise that two dogs are chasing a cat, it follows that some animals are moving, but it does not follow that every animal is sleeping. …
-
Using NLP to resolve mismatches between jobseekers and positions in recruitment
Recruiting through online portals has seen a dramatic increase in recent decades and it is challenging for job seekers to evaluate the overwhelming amount of data to efficiently identify positions that align with their skills and qualifications. This research addresses this issue by investigating …
-
Misinformation Retrieval
… track used for evaluation purposes. I propose a natural language inference (NLI) based approach using CT-BERT to identify tweets that contradict a given fact, used to score documents utilizing the model’s classification probability. The model was trained using a combination of NLI data sets to …
-
Neuro-Symbolic Methods for Natural Language Inference and Question Answering
… state-of-the-art performance on multiple natural language processing benchmarks, those black-box models can hardly provide explanations for their inner mechanisms. They still lack the ability to perform systematic reasoning like human beings and generalize poorly to out-of-distribution …
-
An Inference-Centric Approach to Natural Language Processing and Cognitive Modeling
Reasoning over natural text is highly nuanced, and interpretations can vary widely depending on cultural background, financial status, age, gender, or even mood. This doctoral dissertation seeks to not only mimic human reasoning behaviors but also improve the task used in natural language …
-
Evolving multi-stakeholder discourse on general-purpose artificial intelligence systems and their governance
… mainstream adoption of GPAI. The thesis views language as constitutive of technology governance. Discourse shapes which aspects of technology are considered governable, which interventions are legitimized, and whose expertise is recognized as authoritative. Findings indicate that policy …
-
Understanding and Enhancing the Explainability of Neural Natural Language Inference Models
… led to state-of-the-art performance in numerous natural language processing (NLP) tasks. However, the complexity and opacity of these neural models pose significant challenges for Explainable Artificial Intelligence (XAI). Research has demonstrated that biases and artifacts can spuriously inflate …
-
Information extraction with weak supervision
… of indirect supervision. A novel approach, DSRE-NLI, is introduced, which leverages a Natural Language Inference (NLI) engine and a Semi-Automatic Relation Verbalization (SARV) mechanism to diagnose and mitigate label noise in distantly supervised RE tasks. This method enhances the semantic …
-
Between Language and Models: Rethinking Algorithms for Encoding and Decoding Text
Language models are statistical models that operate over real numbers, taking in a sequence of continuous vectors as input and producing a new continuous vector as output. However, users of language models need to interface with human-readable text. This is made possible by two processes: at the …
-
Characterizing and Detecting Software Attack Surface Components
… we propose two new generic approaches based on Language Models (LM) that can be used to detect different types of attack surface components. 1) A probability-based classification approach using novel term weighting technique; 2) A novel Natural Language Inference (NLI) model based on pre-trained …