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 “"Neural Language Models"”.
-
Neural language models and human linguistic knowledge
Language is one of the hallmarks of intelligence, demanding explanation in a theory of human cognition. However, language presents unique practical challenges for quantitative empirical research, making many linguistic theories difficult to test at naturalistic scales. Artificial neural network …
-
Improving neural language models on low-resource creole languages
When using neural models for NLP tasks, like language modelling, it is difficult to utilize a language with little data, also known as a low-resource language. Creole languages are frequently low-resource and as such it is difficult to train neural language models for them well. Creole languages …
-
Measuring and Manipulating State Representations in Neural Language Models
Modern neural language models (LMs) are typically pre-trained with a self-supervised objective: they are presented with texts that have piece(s) withheld, and asked to generate the withheld portions of the text. By simply scaling up such training, LMs have been able to achieve remarkable …
-
Interpretable semantic representations from neural language models and computer vision
… linguistics is dominated by high capacity neural models that in many cases outperform even human baselines on a wide variety of language-based tasks. However, a serious drawback to the development of these semantic models is in the ambiguity of these representations, as the dimensions of …
-
Conditional Neural Language Models for Multimodal Learning and Natural Language Understanding
In this thesis we introduce conditional neural language models based on log-bilinear and recurrent neural networks with applications to multimodal learning and natural language understanding. We first introduce a LSTM encoder for learning visual-semantic embeddings for ranking the relevance of text …
-
Language Comprehension, Production, and Reasoning in Humans and Neural Language Models
How closely do neural language models mirror human language processing, and what can this alignment teach us about cognition? This dissertation presents convergent evidence in comprehension, production, and reasoning that neural language models (LMs) can serve as productive instruments for …
-
On the evaluation and application of neural language models for grammatical error detection
Neural language models (NLM) have become a core component in many downstream applications within the field of natural language processing, including the task of data-driven automatic grammatical error detection (GED). This thesis explores whether information from NLMs can positively transfer to GED …
-
CALaMo: a Construsctionist perspective on the Analysis of linguistic behaviour of Language Models
In recent years, Neural Language Models (NLMs) have consistently demonstrated increasing linguistic abilities. However, the extent to which such networks can actually learn grammar remains an object of investigation, and experimental results are often inconclusive. Notably, the mainstream …
-
Interactions Between Syntax and Semantics in Language Models
How do syntax and semantics interact in neural language models? Is the intuitive dichotomy between semantics and syntax useful as a mental model of their behavior? In this thesis, I systematically investigate how models handle the interactions between sentence corruptions of each kind. I develop a …
-
Algorithms for Understanding and Fighting Infectious Disease
… disease. Finally, this thesis develops neural language models that can predict how pathogens mutate to evade human immunity, potentially enabling more broadly effective vaccines and therapies. Taken together, this thesis outlines a highly interdisciplinary, algorithmic approach to …
-
Language Models Predict Drug Resistance from Complex Sequence Variation
… antiviral drugs, and antibiotics. Recently, neural language models trained on viral protein sequence evolution have shown promise in their ability to predict viral escape mutations, potentially enabling more intelligent therapeutic design [6]. Hie et al.’s work puts forth the key conceptual …
-
Explainable Multi-Step Reasoning Over Natural Language
… significant progress of reasoning over natural language in the recent years, multi-step natural language reasoning is still a great challenge to the current algorithms. The challenges come from three aspects. First, some multi-step reasoning problems require the retrieval of evidence from large …
-
Linguistically Differentiating Acts and Recalls of Racial Microaggressions on Social Media
… intentions. In this study, we analyze the language used in online racial microaggressions ("Acts") and compare it to personal narratives recounting experiences of such aggressions ("Recalls") by Black social media users. We curated a corpus of acts and recalls from social media discussions …
-
Cause, Composition, and Structure in Language
… new thoughts through writing, humans use language in a remarkably flexible, robust, and creative way. In this thesis, I present three case studies supporting the overarching hypothesis that linguistic knowledge in the human mind can be understood as hierarchically-structured causal …
-
Learning Language with Multimodal Models
Language acquisition by children and machines is remarkable. Yet while children learn from hearing a relatively modest amount of language and by interacting with people and the environment around them, neural language models require far more data and supervision, struggle with generalizing to new …
-
Similarity-Augmented Prediction Methods for Neural Machine Translation
Neural language models (LMs) are now the dominant approach to most tasks in natural language processing (NLP), including machine translation (MT). In spite of their success, studies have shown systematic problems in these models such as the high dispersal of probability mass across vastly many …
-
Towards an Artificial Neuroscience: Analytics for Language Model Interpretability
The growing deployment of neural language models demands greater understanding of their internal mechanisms. The goal of this thesis is to make progress on understanding the latent computations within large language models (LLMs) to lay the groundwork for monitoring, controlling, and aligning …
-
Controlling Neural Language Generation
Large-scale neural language models have made impressive strides in natural language generation. However, typical models operate in a left-to-right, unconstrained fashion with limited control over what is generated. This thesis explores flexible sequence models and weakly supervised methods to …