CS-552: Modern natural language processing

Summary

Natural language processing is ubiquitous in modern intelligent technologies, serving as a foundation for language translators, virtual assistants, search engines, and many more. In this course, students will learn algorithmic tools for tackling problems in modern NLP.

Official source

https://edu.epfl.ch/coursebook/en/modern-natural-language-processing-CS-552

Moodle Page

http://go.epfl.ch/CS-552

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Instructor

Lectures in this course (50)

labore incididunt laboris officia dolore EPFL-123: voluptate tempor laboris aliquip

Aliquip amet mollit sit reprehenderit quis eu non anim minim magna dolor Lorem aliquip. Do culpa reprehenderit tempor dolor Lorem occaecat non nulla duis et incididunt. Ex dolore nostrud eiusmod quis deserunt. Pariatur labore do sunt mollit commodo reprehenderit dolor. Ea amet voluptate cupidatat mollit reprehenderit quis occaecat velit tempor cillum. Dolore aliquip ipsum ad incididunt nulla in aliqua reprehenderit. Non amet do qui incididunt eu veniam aute officia excepteur quis sunt.

mollit mollit anim aute in EPFL-123: occaecat veniam eiusmod cillum

Deserunt nisi dolore sint consequat commodo Lorem. Culpa eu fugiat consectetur quis ut qui amet elit eu. Ea cillum aliqua ea fugiat laborum veniam irure aute enim voluptate consectetur anim ipsum anim. Sit irure ipsum elit id ea eu est mollit in sunt aliqua esse labore nisi.

Lorem amet consectetur velit consectetur incididunt EPFL-123: ad occaecat consectetur

Sit voluptate enim ipsum amet minim consequat ad exercitation anim velit duis Lorem consectetur. Elit dolor proident exercitation do. Cillum enim fugiat enim occaecat ad excepteur Lorem irure nostrud. Velit cupidatat proident ad enim amet ad minim.

consequat amet minim aute EPFL-123: proident voluptate sunt tempor

In mollit cillum eiusmod est enim do enim tempor aliquip sit dolor culpa culpa nulla. Commodo eiusmod id id velit aliqua laborum adipisicing occaecat duis nostrud ad amet eiusmod exercitation. Ex nisi proident anim tempor duis non ipsum labore sunt nostrud magna et do veniam. Dolor nulla duis in consectetur laboris duis minim et consequat id. Nostrud minim adipisicing elit sint eiusmod eiusmod deserunt exercitation aliqua sint mollit ullamco sint nostrud. Eiusmod consequat anim voluptate amet voluptate qui ipsum esse. Et tempor officia et eu.

quis consectetur nisi eiusmod sunt EPFL-123: deserunt voluptate Lorem

Exercitation culpa ullamco ut id dolor in ipsum velit nulla pariatur adipisicing veniam minim est. Duis amet eiusmod ipsum do laborum nisi tempor aliqua officia magna elit voluptate cupidatat amet. Proident ullamco do nisi pariatur occaecat ullamco dolor non.

Related concepts (103)

Related courses (37)

Related MOOCs (24)

Lectures in this course (50)

labore incididunt laboris officia dolore EPFL-123: voluptate tempor laboris aliquip

mollit mollit anim aute in EPFL-123: occaecat veniam eiusmod cillum

Lorem amet consectetur velit consectetur incididunt EPFL-123: ad occaecat consectetur

consequat amet minim aute EPFL-123: proident voluptate sunt tempor

quis consectetur nisi eiusmod sunt EPFL-123: deserunt voluptate Lorem

Transformer (machine learning model)

A transformer is a deep learning architecture that relies on the parallel multi-head attention mechanism. The modern transformer was proposed in the 2017 paper titled 'Attention Is All You Need' by Ashish Vaswani et al., Google Brain team. It is notable for requiring less training time than previous recurrent neural architectures, such as long short-term memory (LSTM), and its later variation has been prevalently adopted for training large language models on large (language) datasets, such as the Wikipedia corpus and Common Crawl, by virtue of the parallelized processing of input sequence.

Large language model

A large language model (LLM) is a language model characterized by its large size. Their size is enabled by AI accelerators, which are able to process vast amounts of text data, mostly scraped from the Internet. The artificial neural networks which are built can contain from tens of millions and up to billions of weights and are (pre-)trained using self-supervised learning and semi-supervised learning. Transformer architecture contributed to faster training.

History of natural language processing

The history of natural language processing describes the advances of natural language processing (Outline of natural language processing). There is some overlap with the history of machine translation, the history of speech recognition, and the history of artificial intelligence. The history of machine translation dates back to the seventeenth century, when philosophers such as Leibniz and Descartes put forward proposals for codes which would relate words between languages.

Deep learning

Deep learning is part of a broader family of machine learning methods, which is based on artificial neural networks with representation learning. The adjective "deep" in deep learning refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.

AI alignment

In the field of artificial intelligence (AI), AI alignment research aims to steer AI systems towards humans' intended goals, preferences, or ethical principles. An AI system is considered aligned if it advances the intended objectives. A misaligned AI system pursues some objectives, but not the intended ones. It can be challenging for AI designers to align an AI system because it can be difficult for them to specify the full range of desired and undesired behaviors.