Lecture

Neuro-symbolic Representations: Commonsense Knowledge & Reasoning

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Description

This lecture explores neuro-symbolic representations for understanding commonsense knowledge and reasoning, focusing on the challenges of providing machines with large-scale commonsense knowledge. It delves into the concept of commonsense knowledge, the representation of such knowledge, and the reasoning processes involved. The instructor discusses the limitations of deep learning in natural language processing and the shortcomings of neural approaches compared to symbolic approaches. The lecture also covers the application of neural and symbolic approaches in representing and reasoning about commonsense knowledge, emphasizing the importance of structured knowledge graphs. Additionally, it addresses the challenges of prior approaches and introduces a framework for training knowledge models from language models trained on raw text.

Official source

Ontological neighbourhood

Information engineering

Machine learning: Artificial neural networks

Related concepts (32)

Knowledge graph

In knowledge representation and reasoning, knowledge graph is a knowledge base that uses a graph-structured data model or topology to integrate data. Knowledge graphs are often used to store interlinked descriptions of entities - objects, events, situations or abstract concepts - while also encoding the semantics underlying the used terminology. Since the development of the Semantic Web, knowledge graphs are often associated with linked open data projects, focusing on the connections between concepts and entities.

Artificial intelligence

Artificial intelligence (AI) is the intelligence of machines or software, as opposed to the intelligence of human beings or animals. AI applications include advanced web search engines (e.g., Google Search), recommendation systems (used by YouTube, Amazon, and Netflix), understanding human speech (such as Siri and Alexa), self-driving cars (e.g., Waymo), generative or creative tools (ChatGPT and AI art), and competing at the highest level in strategic games (such as chess and Go).

Knowledge-based systems

A knowledge-based system (KBS) is a computer program that reasons and uses a knowledge base to solve complex problems. The term is broad and refers to many different kinds of systems. The one common theme that unites all knowledge based systems is an attempt to represent knowledge explicitly and a reasoning system that allows it to derive new knowledge. Thus, a knowledge-based system has two distinguishing features: a knowledge base and an inference engine.

Knowledge

Knowledge is a form of awareness or familiarity. It is often understood as awareness of facts or as practical skills, and may also mean familiarity with objects or situations. Knowledge of facts, also called propositional knowledge, is often defined as true belief that is distinct from opinion or guesswork by virtue of justification. While there is wide agreement among philosophers that propositional knowledge is a form of true belief, many controversies in philosophy focus on justification.

Knowledge representation and reasoning

Knowledge representation and reasoning (KRR, KR&R, KR2) is the field of artificial intelligence (AI) dedicated to representing information about the world in a form that a computer system can use to solve complex tasks such as diagnosing a medical condition or having a dialog in a natural language. Knowledge representation incorporates findings from psychology about how humans solve problems and represent knowledge in order to design formalisms that will make complex systems easier to design and build.

Related lectures (64)

Neuro-symbolic Representations: Commonsense Knowledge & Reasoning

Delves into neuro-symbolic representations for commonsense knowledge and reasoning in natural language processing applications.

Deep Learning for Question Answering

Explores deep learning for question answering, analyzing neural networks and model robustness to noise.

Knowledge Representation: Introduction

Covers knowledge representation in AI, logical inference, and applications in various domains.

Contextual Representations: ELMO and BERT Overview

Covers contextual representations in NLP, focusing on ELMO and BERT architectures and their applications in various tasks.

Vision-Language-Action Models: Training and Applications