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 46 for “"Commonsense reasoning"”.
-
Improving commonsense reasoning in multimodal models
… world by filling in observational gaps through commonsense knowledge and reasoning. Although large-scale foundation models have achieved strong performance on commonsense benchmarks, they struggle to reason beyond surface-level patterns, particularly in novel and ambiguous settings. This thesis …
-
Commonsense reasoning about social dynamics in text
… conversation partner, and respond accordingly. Reasoning about social relationships in text is natural for most people, but is challenging for natural language processing models, in part because these relationships are often subtle, nuanced, and implicit. Training models for this type of …
-
Housekeep: Tidying Virtual Households using Commonsense Reasoning
We introduce Housekeep, a benchmark to evaluate commonsense reasoning in the home for embodied AI. In Housekeep, an embodied agent must tidy a house by rearranging misplaced objects without explicit instructions specifying which objects need to be rearranged. Instead, the agent must learn from and …
-
Using Extended Logic Programs to Formalize Commonsense Reasoning
In this dissertation, we investigate how commonsense reasoning can be formalized by using extended logic programs. In this investigation, we first use extended logic programs to formalize inheritance hierarchies with exceptions by adopting McCarthy's simple abnormality formalism to express …
-
Vision and language : representation learning, commonsense reasoning, and consistency
… with the overarching aim of improving alignment, reasoning, and consistency in multimodal systems. First, we address the problem of fine-grained alignment between vision and language. We propose a semi-supervised grounding mechanism that leverages a pre-trained phrase grounding model to generate …
-
A First Study of Generative CommonSense Reasoning in Greek
… και η παραγωγική συλλογιστική κοινής λογικής (commonsense reasoning) αποτελούν διαχρονικά προκλήσεις στον τομέα της Επεξεργασίας Φυσικής Γλώσσας (Natural Language Processing), ιδίως για γλώσσες χαμηλών πόρων, όπως η ελληνική. Η παρούσα διπλωματική εργασία διερευνά την απόδοση ελληνικών …
-
Time-Situated Metacognitive Agency and Other Aspects of Commonsense Reasoning
Much research in commonsense reasoning (CSR) involves use of external representations of an agent's reasoning, based on compelling features of classical logic. However, these advantages come with severe costs, including: omniscience, consistency, static semantics, frozen deadlines, lack of …
-
Enhancing diversity in generative commonsense reasoning for explaining relationships between concepts
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2023-09-01 without embargo terms
-
ΑΝΑΠΑΡΑΣΤΑΣΗ ΓΝΩΣΗΣ ΓΙΑ ΥΠΟΣΤΗΡΙΞΗ ΕΞΑΓΩΓΗΣ ΣΥΜΠΕΡΑΣΜΑΤΩΝ ΚΟΙΝΗΣ ΛΟΓΙΚΗΣ.
… INTELLIGENCE FIELD OF COMPUTER SCIENCE, IS THE REASONING PROBLEM. RECENTLY, THE RESEARCHERS OF AI INTERESTED IN COMMONSENSE REASONING AS IT IS DEFINED BY CERTAIN CHARACTERISTICS, MAINLY THE NON - MONOTONICITY DUE TO EXCEPTIONS TO GENERAL RULES, THE CONFLICTED INFORMATION DUE TO MULTIPLE …
-
Commonsense for Zero-Shot Natural Language Video Localization
… this work, we investigate the effectiveness of commonsense reasoning in zero-shot NLVL. Specifically, we present CORONET, a zero-shot NLVL framework that utilizes commonsense information to bridge the gap between videos and generated pseudo-queries through a commonsense enhancement module. Our …
-
Practical artificial commonsense
… speed and accuracy of such machines, can draw on commonsense intuitions to effortlessly improvise novel solutions to unexpected problems. The objective of artificial commonsense is to bring some measure of this powerful mental agility and understanding to robots and software systems. In this …
-
An Ontology-Oriented Approach to Represent and Compare the Functional Behaviour of Event-Based Systems
… representation must support machine-assisted reasoning mechanism as well as human intuitions. We present an effective, ontology-oriented formal approach of representation that is designed to be both machine-processable and human comprehensible. Based on the theory of events and change in …
-
Commonsense agent reasoning by exploiting knowledge graphs and computational argumentation
Commonsense agents are intelligent agents that use commonsense knowledge and commonsense reasoning in order to perform a task on behalf of or take a decision to help a human user, usually in open environments, which are dynamic, partially observable, and non-deterministic, where agents possess …
-
Implicatures in Continuation-Based Dynamic Semantics by Reasoning in the Context
… elaborate context structure to allow for basic commonsense reasoning, and show how this can be used to capture implicature-related content with typical instances from three classes of meaning: Grice [1975]'s conversational implicatures; Grice [1975]'s conventional implicatures, with a focus on …
-
Complex Multi-step Inference over Knowledge Graphs Leveraging Large Language Models, Probabilistic, and Logical Reasoning
… Despite this widespread adoption, reasoning on KGs presents unique challenges. The data in real-world KGs is often uncertain, noisy, and incomplete, and its structured format demands interaction through specialized query languages, posing a challenge for inexpert users who express …
-
Extracting and Inferring Personal Attributes from Dialogue
… verbatim in utterances and instead requires commonsense reasoning and lexical inferences, which occur frequently in everyday conversation.
-
Visual question answering with contextualized commonsense knowledge
… In this work, we focus on questions that require commonsense reasoning. In contrast to previous methods which inject knowledge from static knowledge bases, we investigate the incorporation of contextualized knowledge using Commonsense Transformer (COMET), an existing knowledge model trained on …
-
Weakly-supervised geometry-aware novel view synthesis
… image generation, and paves the way for commonsense reasoning. Our work has potential applications in augmented reality and visual effects, with further exploration of the model's capabilities and integration into broader systems for enhanced visual understanding.
-
Towards Intelligent Conversational Assistants: Enhancing Task-Oriented Dialogue Systems with Knowledge Integration
… transfer mechanism is proposed to improve commonsense reasoning in low-resource languages, expanding the multilingual adaptability of TOD systems. By integrating structured knowledge across different levels, it enhances system performance in user intent recognition, dialogue state tracking, …
-
Answering questions about dynamic domains from natural language using ASP
… answers. We also used this research to test our reasoning techniques, such as reasoning in dynamic domains, where movement is involved, and reasoning about changes in cardinalities. The original discourse was written in our controlled language MCL , which allowed us to remove a variety of natural …
Page 1 of 3