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 28 for “"Commonsense Knowledge"”.

  1. A Turing Game for commonsense knowledge extraction

    Commonsense is of primary interest to AI research since the inception of the field. Traditionally, commonsense knowledge is gathered by using humans to create and insert it in knowledge bases. Automating the collection of commonsense from text that is freely available can reduce the cost and effort …

    uiuc Repository record for A Turing Game for commonsense knowledge extraction (opens in a new tab)

  2. Expanding commonsense knowledge bases by learning from image tags

    I present a method for learning new commonsense facts to augment existing commonsense knowledge bases by using the metadata of large online image collections. Online image collections present a source of knowledge that is supported by many contributors, has good representation of objects and their …

    uiuc Repository record for Expanding commonsense knowledge bases by learning from image tags (opens in a new tab)

  3. Learning commonsense knowledge from the interpretation of individual experiences

    … intelligence, we need to discover how we learn commonsense knowledge. We humans are able to infer generalizations of knowledge, make predictions about the future, and answer questions based on what we've experienced. In this thesis I present a method for performing these commonsense tasks in an …

    mit Repository record for Learning commonsense knowledge from the interpretation of individual experiences (opens in a new tab)

  4. Using analogy to acquire commonsense knowledge from human Contributors

    … goal of the work reported here is to capture the commonsense knowledge of non-expert human contributors. Achieving this goal will enable more intelligent human-computer interfaces and pave the way for computers to reason about our world. In the domain of natural language processing, it will …

    mit Repository record for Using analogy to acquire commonsense knowledge from human Contributors (opens in a new tab)

  5. STaRS.sys: designing and building a commonsense-knowledge enriched wordnet for therapeutic purposes

    … to exploit human language resources and knowledge extraction techniques to build STaRS.sys, a software system designed to support therapists in the rehabilitation of Italian anomic patients. After an introductory section reviewing classification, assessment, and remediation methods for …

    trento Repository record for STaRS.sys: designing and building a commonsense-knowledge enriched wordnet for therapeutic purposes (opens in a new tab)

  6. A Composite Syntactic-Semantic Interpretable Text Entailment Approach Exploring Commonsense Knowledge Graphs

    … some scenario to the detriment of another. The commonsense world knowledge necessary to support more complex inferences is also usually employed in a limited way, with most approaches sticking to shallow semantic information, leaving more elaborate semantic relationships aside. Furthermore, most …

    passau-thes Repository record for A Composite Syntactic-Semantic Interpretable Text Entailment Approach Exploring Commonsense Knowledge Graphs (opens in a new tab)

  7. A commonsense approach to story understanding

    … stories. Understanding stories requires commonsense knowledge. Many story understanding systems rely on rules to express and manipulate common sense, but the amount of common sense is vast and expressing significant amounts of common sense this way is tedious. Commonsense knowledge bases …

    mit Repository record for A commonsense approach to story understanding (opens in a new tab)

  8. Improving an image annotation and retrieval agent using commonsense and personal knowledge

    … is proposed. This agent, ARIA, will combine commonsense knowledge, specific personal background information about the user, and the context in which they will use the images to assist him/her in the process of locating and using his/her images. The act of composing an email or webpage …

    mit Repository record for Improving an image annotation and retrieval agent using commonsense and personal knowledge (opens in a new tab)

  9. Efficient Information Extraction Using Statistical Relational Learning

    … supervised examples for relations by using commonsense knowledge. The key innovation is that this commonsense knowledge is completely independent of the natural language text. This helps when learning the full model for information extraction as against simply learning the parameters of a …

    wfu Repository record for Efficient Information Extraction Using Statistical Relational Learning (opens in a new tab)

  10. MEng Thesis: Incorporating Structured Commonsense into Language Models

    … by infusing them with information found in commonsense knowledge bases. Commonsense is basic knowledge about the world that humans are expected to have and is needed to achieve efficient communication. Often times, to understand texts, a person must use their commonsense to make implicit …

    mit Repository record for MEng Thesis: Incorporating Structured Commonsense into Language Models (opens in a new tab)

  11. Qualitative reasoning about fluids and mechanics

    Understanding people's commonsense knowledge about physical world is a fundamental problem in building intelligent systems. If this knowledge can be represented and used by computers, they can duplicate people's ability to understand and interact with the world. Qualitative physics is the attempt …

    uiuc Repository record for Qualitative reasoning about fluids and mechanics (opens in a new tab)

  12. Learning commonsense categorical knowledge in a thread memory system

    … acquire, and reason about the kinds of commonsense knowledge that we humans have about the world. This endeavor suggests steps such as identifying the kinds of knowledge people commonly have about the world, constructing suitable knowledge representations, and exploring the mechanisms …

    mit Repository record for Learning commonsense categorical knowledge in a thread memory system (opens in a new tab)

  13. Leveraging Multimodal Perspectives to Learn Common Sense for Vision and Language Tasks

    … multiple modalities, and to use large amounts of commonsense knowledge while performing visual or textual tasks. Inspired by that ability, we approach commonsense learning as leveraging perspectives from multiple modalities for images and text in the context of vision and language tasks. Given a …

    vt Repository record for Leveraging Multimodal Perspectives to Learn Common Sense for Vision and Language Tasks (opens in a new tab)

  14. Resolution of linear entity and path geometries expressed via partially-geospatial natural language

    … language, people typically combine implicit, commonsense knowledge with explicitly-stated information. Usually, much of this is contextual and relies on establishing locations by relating them to other locations mentioned earlier in the conversation. Because people and objects move through the …

    mit Repository record for Resolution of linear entity and path geometries expressed via partially-geospatial natural language (opens in a new tab)

  15. i-Seek : an intelligent system for eliciting and explaining knowledge

    … Intelligent System for Eliciting and Explaining Knowledge that leverages the OpenMind [1] Commonsense knowledge base in conjunction with domain- specific knowledge in Personal Finance, Technical Help, and Health domains to act as an advisory system for novice users. Most of the interfaces are …

    mit Repository record for i-Seek : an intelligent system for eliciting and explaining knowledge (opens in a new tab)

  16. MOOIDE : natural language interface for programming MOO environments

    … in programming. However, those systems lacked commonsense knowledge. MOOIDE brings commonsense features to natural language programming in addition to parsing. Commonsense reasoning allows MOOIDE to automatically include typical object properties, verb affordances and affordance rules as well …

    mit Repository record for MOOIDE : natural language interface for programming MOO environments (opens in a new tab)

  17. Augmenting anomaly detection for autonomous vehicles with symbolic rules

    … I address these issues through the use of a commonsense knowledge base, a predefined set of rules regarding driving behavior, and a means of updating the base set of rules as anomalies are detected. In order to explore this problem I have built a hardware platform that was used to evaluate …

    mit Repository record for Augmenting anomaly detection for autonomous vehicles with symbolic rules (opens in a new tab)

  18. Raconteur : intelligent assistance for conversational storytelling with media libraries

    … a few sentences in unrestricted English. A large commonsense knowledge base and a novel commonsense inference technique are used to understand event relations and determine narration similarity using concept vector computation that goes beyond keyword matching or word co-occurrence based …

    mit Repository record for Raconteur : intelligent assistance for conversational storytelling with media libraries (opens in a new tab)

  19. Discovering Abstractions from Language via Neurosymbolic Program Synthesis

    … Drawing on human language as a source of commonsense knowledge, Lilo learns abstractions that would be intractable to discover with traditional enumerative search. In our evaluations against DreamCoder, a state-of-the-art library learning algorithm, we find that Lilo solves more tasks …

    mit Repository record for Discovering Abstractions from Language via Neurosymbolic Program Synthesis (opens in a new tab)

  20. EventMinder : a personal calendar assistant that understands events

    … because it involves integrating many types of knowledge: commonsense knowledge, about common events and the particular instances in the world, and user knowledge about the individual's preferences and goals. In this thesis, I present two models of event understanding: RoMULUS and JULIUS. …

    mit Repository record for EventMinder : a personal calendar assistant that understands events (opens in a new tab)

Page 1 of 2