Lecture

Modern Natural Language Processing: Core Methods and Applications

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 covers core methods in modern natural language processing, including word embeddings, recurrent neural networks, transformers, and text generation. It explores the challenges and opportunities in NLP, such as ethical considerations, robustness, and hallucination. The instructor discusses the latest advancements in NLP models, the importance of multimodal data, and the applications of NLP in various fields like medicine and law.

This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.

Watch on Mediaspace

Official source

Related concepts (32)

Recurrent neural network

A recurrent neural network (RNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. In contrast to uni-directional feedforward neural network, it is a bi-directional artificial neural network, meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.

Law

Law is a set of rules that are created and are enforceable by social or governmental institutions to regulate behavior, with its precise definition a matter of longstanding debate. It has been variously described as a science and as the art of justice. State-enforced laws can be made by a group legislature or by a single legislator, resulting in statutes; by the executive through decrees and regulations; or established by judges through precedent, usually in common law jurisdictions.

Feedforward neural network

A feedforward neural network (FNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. Its flow is uni-directional, meaning that the information in the model flows in only one direction—forward—from the input nodes, through the hidden nodes (if any) and to the output nodes, without any cycles or loops, in contrast to recurrent neural networks, which have a bi-directional flow.

By-law

A by-law (bye-law, by(e)law, by(e) law), or as it is most commonly known in the United States bylaws, is a set of rules or law established by an organization or community so as to regulate itself, as allowed or provided for by some higher authority. The higher authority, generally a legislature or some other government body, establishes the degree of control that the by-laws may exercise. By-laws may be established by entities such as a business corporation, a neighbourhood association, or depending on the jurisdiction, a municipality.

Artificial neural network

Artificial neural networks (ANNs, also shortened to neural networks (NNs) or neural nets) are a branch of machine learning models that are built using principles of neuronal organization discovered by connectionism in the biological neural networks constituting animal brains. An ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit a signal to other neurons.

Related lectures (64)

Language Models: Fixed-context and Recurrent Neural Networks

Discusses language models, focusing on fixed-context neural models and recurrent neural networks.

Deep Neural Networks: Optimization and Approximation

Explores optimization and approximation in deep neural networks, including optimal control and numerical experiments.

Neural Networks: Two Layers Neural Network

Covers the basics of neural networks, focusing on the development from two layers neural networks to deep neural networks.

Building Physical Neural Networks

Discusses challenges in building physical neural networks, focusing on depth, connections, and trainability.

Deep Generative Models: Part 2

Explores deep generative models, including mixtures of multinomials, PCA, deep autoencoders, convolutional autoencoders, and GANs.

Related concepts (32)

Recurrent neural network

Law

Feedforward neural network

By-law

Artificial neural network