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 14 of 14 for “"Compositional generalization"”.
-
Neural computational mechanism of compositional generalization
… understanding of the representation subserving compositional generalization: how reusable knowledge is acquired from experience, how it is represented in the brain, and what are the computations over the representations that support generalization in novel situations. In Chapter 1, I presented …
-
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 …
-
mSCAN - a Multilingual Dataset for Compositional Generalization Evaluation
… on a variety of tasks, yet still struggle on compositional generalization benchmarks. The majority of these benchmarks evaluate performance in English only, leaving open the question of whether these results generalize to other languages. As an initial step to answering this question, we …
-
Unifying Neural and Symbolic Computation for Compositional Generalization: Representation and Processing
… achievements, often fall short of the robust compositional generalization that characterizes human cognition, particularly in tasks demanding symbolic manipulation and algorithmic reasoning. This dissertation investigates the mechanisms underlying compositional generalization in neural …
-
ZERO-SHOT COMPOSITIONAL EVENT DETECTION VIA GRAPH MODULAR NETWORK
… supervised sequence tagging models lack the compositional generalization ability. We present a model that is able to achieve zero-shot compositional generalization for event detection. Our model, named compositional graph modular network (CGMN), proposes two separate graph neural networks to …
-
Compositional Linguistic Generalization in Artificial Neural Networks
Compositionality---the principle that the meaning of a complex expression is built from the meanings of its parts---is considered a central property of human language. This dissertation focuses on compositional generalization, a key benefit of compositionality that enables the production and …
-
Explainable Multi-Step Reasoning Over Natural Language
… Third, neural language models suffer from compositional generalization issues when solving multi-step reasoning problems, meaning that when the models are trained on simple tasks but tested on the hard tasks that require more reasoning steps than in training, they tend to fail. In this …
-
Developing Informative and Faithful Image Captioning Systems with Compositional Generalizability
… \textit{Informativeness}, and \textit{Compositional Generalization}. In this thesis, we attempt to realize the above goals from several different aspects: (1) Designing caption-guided visual relation graphs that can better bridge modalities to generate better captions with fidelity; (2) …
-
Assessing and Improving Generalization in Graph Reasoning and Learning
… tasks. Each article investigates and improves generalization in one of several graph reasoning applications: classical graph classification tasks, compositional visual reasoning, and the novel task of parameter prediction for neural network graphs. In the first article we study the attention …
-
Neuro-symbolic program generation and execution for hybrid reasoning
… including explainability, efficiency, compositionality, and robustness that are sorely lacking in the monolithic deep neural networks today. A well-designed interface between deep learning and symbolic reasoning provides a structural learning prior that can lead to performance …
-
Compact Discrete Representations for Scalable Similarity Search
… Going beyond binary codes, we will highlight a compositional generalization of k-means clustering which maps data points onto integer codes with storage and search costs that grow sub-linearly in the number of cluster centers. This representation improves upon binary codes, and provides an even …
-
Transfer in sequential decision making
… and study a modular architecture design for compositional generalization in multi-modal multi-task settings. Controlled experiments demonstrate zero-shot transfer on held-out compositions of observation, action and instruction spaces, as well as efficient integration of new observation …
-
Adversarial Déjà Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen Attacks
… by rethinking jailbreak robustness through a compositional and data-centric lens. We introduce the Adversarial Déjà Vu hypothesis, which posits that ostensibly novel jailbreak attacks are rarely new in kind, but instead arise from recombinations of a finite set of recurring adversarial skills. …