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 20 of 39 for “"Compositionality"”.
-
Geometry of compositionality
Word embedding is a popular representation of words in vector space, and its geometry reveals the lexical semantics. This thesis further explores the interesting geometric properties of word embedding, and looks into its interaction with the context representation. We propose an innovative method …
-
Problems of compositionality
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Linguistics and Philosophy, 1995.
-
Meaning and compositionality as statistical induction of categories and constraints
What do words and phrases mean? How do we infer their meaning in a given context? How do we know which sets of words have sensible meanings when combined, as opposed to being nonsense? As language learners and speakers, we can solve these problems starting at a young age, but as scientists, our …
-
Towards more human-like concept learning in machines : compositionality, causality, and learning-to-learn
… framework that utilizes the principles of compositionality, causality, and learning-to-learn to learn good programs from just one or a handful of examples of a new concept. New conceptual representations can be learned compositionally from pieces of related concepts, where the pieces …
-
Modus representandi et componendi: An idolatrous, numerically-schismatic compte rendu of modes of representation and compositionality
Esta tesis germinó a partir de dos lecturas formativas que dejaron una impresión complementaria y duradera: The Revenge of the Given de Jerry Fodor y Representational Genera de John Haugeland. Si bien la primera inspiró un trabajo previo publicado en la revista Biosemiotics, fue la segunda —y sus …
-
Factorization and Compositional Generalization in Diffusion Models
… the defining features of human intelligence is compositionality—the ability to generate an infinite array of complex ideas from a limited set of components. This capacity allows for the creation of novel and intricate combinations of arbitrary concepts, enabling potentially infinite expressive …
-
Enabling Compositional Generalization of AI Systems
… thesis aims to bridge this gap by incorporating compositionality into deep neural networks, thereby enhancing their ability to generalize and solve novel and complex tasks, such as generating 2D images and 3D assets based on complicated specifications, or enabling humanoid agents to perform a …
-
COMPOSITIONAL GENERALIZATION IN INSTRUCTION FOLLOWING TASKS
… use while giving and following instructions is compositionality: the capacity to understand and produce a potentially infinite number of novel combinations from familiar components. This ability is instrumental in being able to learn from limited data and is crucial for instruction following …
-
Human Learning-Augmented Machine Learning Frameworks for Text Analytics
… of text analytics. The first study examined compositionality—how information is decomposed into small pieces, which are then recomposed to generate larger pieces of information. Compositionality is considered as a fundamental cognitive process, and also one of the best explanations for …
-
Baba is AI: A Grounded Benchmark for Compositional Generalization in Dynamic Rule Systems
… is known as generalization through systematic compositionality. Developing agents that can use systematic compositionality to generalize to new conditions has been a long-standing problem in AI. In response to this challenge, grounded benchmarks have been developed to evaluate an agent’s …
-
Opinion Analysis through Constraint Optimisation
… of a weighted polarity lexicon. Firstly, compositionality rules simply become linear sums without requiring conflict resolution rules. Secondly, a weighted polarity lexicon can be automatically learnt from review data using constraint optimisation. Thirdly, instead of providing just a …
-
Preference inference based on lexicographic and Pareto models
… under some set of preference models. (Strong) compositionality is a property of preference statements in connection with a set of preference models. It demands inference of preference statements for certain combinations of preference models. We find many interesting results for this case, which …
-
Disentangling neural network representations for improved generalization
… of features in image classification, language compositionality in goal driven dialog, and latent intention priors in visual dialog. By increasing the generality of neural networks through disentanglement we hope to reduce the effort required to apply neural networks to new tasks and highlight …
-
Compounding in Namagowab and English: (exploring meaning creation in compounds)
… of word formation and an overview of semantic compositionality, structure and productivity, within the broad context of cognitive, lexicalist and distributed morphology paradigms. This coupled with history reading about the languages and its people, is used to speculate about why compounds …
-
The language of emotions in Dalabon (northern Australia)
… in anger. Such compounds rely on analogy and compositionality, with metonymies and metaphors playing minor roles in their production. In fact, analogy and compositionality produce compounds which, in turn, may suggest new metaphors to the speakers. Chapter 11 elaborates upon the idea that …
-
The language of emotions in Dalabon (northern Australia)
… in anger. Such compounds rely on analogy and compositionality, with metonymies and metaphors playing minor roles in their production. In fact, analogy and compositionality produce compounds which, in turn, may suggest new metaphors to the speakers. Chapter 11 elaborates upon the idea that …
-
Reasoning Across Language and Vision in Machines and Humans
… of language and vision exploiting the compositionality inherent in both modalities. I present work indicating that this may be the case. Humans are shown videos while fMRI data is acquired and sentences which describe those videos are recovered compositionally.</p>
-
Compositional Robot Learning for Generalizable Interactions
… explore an alternative approach to incorporate compositionality when there is no explicit compositional structure — using language as an intermediate representation for internal reasoning. We show how this linguistic representation can help robots predict the trajectories of other agents.
-
Combining Functional and Automata Synthesis to Learn Causal Reactive Programs
… is not very interpretable, lacking features like compositionality that characterize human knowledge. Given these shortcomings, we explore a different approach to engineering human-like AI called program synthesis, in which learned knowledge is represented in the form of a symbolic program. …
-
The Problem of the Earth's Figure: Measurement, Theory, and Evidence in Physical Geodesy
… a decisive test of the interactive nature and compositionality of gravitation (c. 1740-1825). I retell how Pierre-Simon Laplace established that the Earth’s external attraction is the resultant force of the mutual attractions between its constituent particles; a momentous but overlooked …
Page 1 of 2