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"”.

  1. 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 …

    mit Repository record for Neural language models and human linguistic knowledge (opens in a new tab)

  2. 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 …

    uiuc Repository record for Improving neural language models on low-resource creole languages (opens in a new tab)

  3. 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 …

    mit Repository record for Measuring and Manipulating State Representations in Neural Language Models (opens in a new tab)

  4. 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 …

    qu-belfast Repository record for Interpretable semantic representations from neural language models and computer vision (opens in a new tab)

  5. 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 …

    toronto-retro Repository record for Conditional Neural Language Models for Multimodal Learning and Natural Language Understanding (opens in a new tab)

  6. 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 …

    mit Repository record for Language Comprehension, Production, and Reasoning in Humans and Neural Language Models (opens in a new tab)

  7. 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 …

    cambridge Repository record for On the evaluation and application of neural language models for grammatical error detection (opens in a new tab)

  8. 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 …

    trento Repository record for CALaMo: a Construsctionist perspective on the Analysis of linguistic behaviour of Language Models (opens in a new tab)

  9. 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 …

    mit Repository record for Interactions Between Syntax and Semantics in Language Models (opens in a new tab)

  10. 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 …

    mit Repository record for Algorithms for Understanding and Fighting Infectious Disease (opens in a new tab)

  11. 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 …

    mit Repository record for Language Models Predict Drug Resistance from Complex Sequence Variation (opens in a new tab)

  12. 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 …

    arizona-thes Repository record for Explainable Multi-Step Reasoning Over Natural Language (opens in a new tab)

  13. 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 …

    vt Repository record for Linguistically Differentiating Acts and Recalls of Racial Microaggressions on Social Media (opens in a new tab)

  14. 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 …

    mit Repository record for Cause, Composition, and Structure in Language (opens in a new tab)

  15. 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 …

    mit Repository record for Learning Language with Multimodal Models (opens in a new tab)

  16. 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 …

    cambridge Repository record for Similarity-Augmented Prediction Methods for Neural Machine Translation (opens in a new tab)

  17. 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 …

    mit Repository record for Towards an Artificial Neuroscience: Analytics for Language Model Interpretability (opens in a new tab)

  18. 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 …

    mit Repository record for Controlling Neural Language Generation (opens in a new tab)