Lecture

Pretraining Sequence-to-Sequence Models: BART + T5

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 the pretraining of sequence-to-sequence models using BART and T5, discussing the concepts of transfer learning, fine-tuning, and the specific architectures of BART and T5. It explains the pretraining process, corruption strategies, and the tasks these models can perform, such as classification and sequence labeling. The lecture also compares the performance of BART and T5 with other models like BERT, UniLM, and XLNet, highlighting their capabilities in various tasks. Additionally, it explores the results of summarization tasks and the references for further reading on the topic.

Official source

Related concepts (18)

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.

Generative pre-trained transformer

Generative pre-trained transformers (GPT) are a type of large language model (LLM) and a prominent framework for generative artificial intelligence. The first GPT was introduced in 2018 by OpenAI. GPT models are artificial neural networks that are based on the transformer architecture, pre-trained on large data sets of unlabelled text, and able to generate novel human-like content. As of 2023, most LLMs have these characteristics and are sometimes referred to broadly as GPTs.

Automatic summarization

Automatic summarization is the process of shortening a set of data computationally, to create a subset (a summary) that represents the most important or relevant information within the original content. Artificial intelligence algorithms are commonly developed and employed to achieve this, specialized for different types of data. Text summarization is usually implemented by natural language processing methods, designed to locate the most informative sentences in a given document.

Text-to-image model

A text-to-image model is a machine learning model which takes an input natural language description and produces an image matching that description. Such models began to be developed in the mid-2010s, as a result of advances in deep neural networks. In 2022, the output of state of the art text-to-image models, such as OpenAI's DALL-E 2, Google Brain's , StabilityAI's Stable Diffusion, and Midjourney began to approach the quality of real photographs and human-drawn art.

Federal enterprise architecture

A federal enterprise architecture framework (FEAF) is the U.S. reference enterprise architecture of a federal government. It provides a common approach for the integration of strategic, business and technology management as part of organization design and performance improvement. The most familiar federal enterprise architecture is the enterprise architecture of the Federal government of the United States, the U.S. "Federal Enterprise Architecture" (FEA) and the corresponding U.S. "Federal Enterprise Architecture Framework" (FEAF).

Related lectures (43)

Transformers: Overview and Self-Attention

Provides an overview of Transformers, self-attention, multi-headed attention, and the Transformer decoder and encoder.

Pretraining: Transformers & Models

Explores pretraining models like BERT, T5, and GPT, discussing their training objectives and applications in natural language processing.

Language Models: From Theory to Computation

Explores the mathematics of language models, covering architecture design, pre-training, and fine-tuning, emphasizing the importance of pre-training and fine-tuning for various tasks.

Transformers: Pretraining and Decoding Techniques

Covers advanced transformer concepts, focusing on pretraining and decoding techniques in NLP.

Graph-to-Graph Transformers: Syntax-aware Graph Encoding