GPT-1

Last updated
Generative Pre-trained Transformer 1 (GPT-1)
Original author(s) OpenAI
Initial releaseJune 2018;6 years ago (June 2018)
Repository
Successor GPT-2
Type
License MIT [1]
Website openai.com/blog/language-unsupervised/   OOjs UI icon edit-ltr-progressive.svg
Original GPT architecture Full GPT architecture.svg
Original GPT architecture

Generative Pre-trained Transformer 1 (GPT-1) was the first of OpenAI's large language models following Google's invention of the transformer architecture in 2017. [2] In June 2018, OpenAI released a paper entitled "Improving Language Understanding by Generative Pre-Training", [3] in which they introduced that initial model along with the general concept of a generative pre-trained transformer. [4]

Contents

Up to that point, the best-performing neural NLP models primarily employed supervised learning from large amounts of manually labeled data. This reliance on supervised learning limited their use of datasets that were not well-annotated, in addition to making it prohibitively expensive and time-consuming to train extremely large models; [3] [5] many languages (such as Swahili or Haitian Creole) are difficult to translate and interpret using such models due to a lack of available text for corpus-building. [5] In contrast, a GPT's "semi-supervised" approach involved two stages: an unsupervised generative "pre-training" stage in which a language modeling objective was used to set initial parameters, and a supervised discriminative "fine-tuning" stage in which these parameters were adapted to a target task. [3]

The use of a transformer architecture, as opposed to previous techniques involving attention-augmented RNNs, provided GPT models with a more structured memory than could be achieved through recurrent mechanisms; this resulted in "robust transfer performance across diverse tasks". [3]

Reason for choosing BookCorpus

BookCorpus was chosen as a training dataset partly because the long passages of continuous text helped the model learn to handle long-range information. [6] It contained over 7,000 unpublished fiction books from various genres. The rest of the datasets available at the time, while being larger, lacked this long-range structure (being "shuffled" at a sentence level). [3]

The BookCorpus text was cleaned by the ftfy library to standardized punctuation and whitespace and then tokenized by spaCy. [3]

Architecture

The GPT-1 architecture was a twelve-layer decoder-only transformer, using twelve masked self-attention heads, with 64-dimensional states each (for a total of 768). Rather than simple stochastic gradient descent, the Adam optimization algorithm was used; the learning rate was increased linearly from zero over the first 2,000 updates to a maximum of 2.5×10−4, and annealed to 0 using a cosine schedule. [3] GPT-1 has 117 million parameters. [4]

While the fine-tuning was adapted to specific tasks, its pre-training was not; to perform the various tasks, minimal changes were performed to its underlying task-agnostic model architecture. [3] Despite this, GPT-1 still improved on previous benchmarks in several language processing tasks, outperforming discriminatively-trained models with task-oriented architectures on several diverse tasks. [3]

Performance and evaluation

GPT-1 achieved a 5.8% and 1.5% improvement over previous best results [3] on natural language inference (also known as textual entailment ) tasks, evaluating the ability to interpret pairs of sentences from various datasets and classify the relationship between them as "entailment", "contradiction" or "neutral". [3] Examples of such datasets include QNLI (Wikipedia articles) and MultiNLI (transcribed speech, popular fiction, and government reports, among other sources); [7] It similarly outperformed previous models on two tasks related to question answering and commonsense reasoning—by 5.7% on RACE, [8] a dataset of written question-answer pairs from middle and high school exams, and by 8.9% on the Story Cloze Test. [9]

GPT-1 improved on previous best-performing models by 4.2% on semantic similarity (or paraphrase detection), evaluating the ability to predict whether two sentences are paraphrases of one another, using the Quora Question Pairs (QQP) dataset. [3]

GPT-1 achieved a score of 45.4, versus a previous best of 35.0 [3] in a text classification task using the Corpus of Linguistic Acceptability (CoLA). Finally, GPT-1 achieved an overall score of 72.8 (compared to a previous record of 68.9) on GLUE, a multi-task test. [10]

Related Research Articles

In artificial intelligence (AI), commonsense reasoning is a human-like ability to make presumptions about the type and essence of ordinary situations humans encounter every day. These assumptions include judgments about the nature of physical objects, taxonomic properties, and peoples' intentions. A device that exhibits commonsense reasoning might be capable of drawing conclusions that are similar to humans' folk psychology and naive physics.

A language model is a probabilistic model of a natural language. In 1980, the first significant statistical language model was proposed, and during the decade IBM performed ‘Shannon-style’ experiments, in which potential sources for language modeling improvement were identified by observing and analyzing the performance of human subjects in predicting or correcting text.

In natural language processing, textual entailment (TE), also known as natural language inference (NLI), is a directional relation between text fragments. The relation holds whenever the truth of one text fragment follows from another text.

<span class="mw-page-title-main">Feature learning</span> Set of learning techniques in machine learning

In machine learning (ML), feature learning or representation learning is a set of techniques that allow a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task.

The Winograd schema challenge (WSC) is a test of machine intelligence proposed in 2012 by Hector Levesque, a computer scientist at the University of Toronto. Designed to be an improvement on the Turing test, it is a multiple-choice test that employs questions of a very specific structure: they are instances of what are called Winograd schemas, named after Terry Winograd, professor of computer science at Stanford University.

Neural machine translation (NMT) is an approach to machine translation that uses an artificial neural network to predict the likelihood of a sequence of words, typically modeling entire sentences in a single integrated model.

<span class="mw-page-title-main">Transformer (deep learning architecture)</span> Deep learning architecture for modelling sequential data

A transformer is a deep learning architecture developed by researchers at Google and based on the multi-head attention mechanism, proposed in the 2017 paper "Attention Is All You Need". Text is converted to numerical representations called tokens, and each token is converted into a vector via lookup from a word embedding table. At each layer, each token is then contextualized within the scope of the context window with other (unmasked) tokens via a parallel multi-head attention mechanism, allowing the signal for key tokens to be amplified and less important tokens to be diminished.

Bidirectional encoder representations from transformers (BERT) is a language model introduced in October 2018 by researchers at Google. It learns to represent text as a sequence of vectors using self-supervised learning. It uses the encoder-only transformer architecture. It is notable for its dramatic improvement over previous state-of-the-art models, and as an early example of a large language model. As of 2020, BERT is a ubiquitous baseline in natural language processing (NLP) experiments.

Generative Pre-trained Transformer 3 (GPT-3) is a large language model released by OpenAI in 2020.

<span class="mw-page-title-main">GPT-2</span> 2019 text-generating language model

Generative Pre-trained Transformer 2 (GPT-2) is a large language model by OpenAI and the second in their foundational series of GPT models. GPT-2 was pre-trained on a dataset of 8 million web pages. It was partially released in February 2019, followed by full release of the 1.5-billion-parameter model on November 5, 2019.

<span class="mw-page-title-main">DALL-E</span> Image-generating deep-learning model

DALL·E, DALL·E 2, and DALL·E 3 are text-to-image models developed by OpenAI using deep learning methodologies to generate digital images from natural language descriptions known as "prompts".

A foundation model, also known as large AI model, is a machine learning or deep learning model that is trained on vast datasets so it can be applied across a wide range of use cases. Generative AI applications like Large Language Models are often examples of foundation models.

<span class="mw-page-title-main">Generative pre-trained transformer</span> Type of large language model

A generative pre-trained transformer (GPT) is a type of large language model (LLM) and a prominent framework for generative artificial intelligence. It is an artificial neural network that is used in natural language processing by machines. It is based on the transformer deep learning architecture, pre-trained on large data sets of unlabeled text, and able to generate novel human-like content. As of 2023, most LLMs had these characteristics and are sometimes referred to broadly as GPTs.

<span class="mw-page-title-main">GPT-J</span> Open source artificial intelligence text generating language model developed by EleutherAI

GPT-J or GPT-J-6B is an open-source large language model (LLM) developed by EleutherAI in 2021. As the name suggests, it is a generative pre-trained transformer model designed to produce human-like text that continues from a prompt. The optional "6B" in the name refers to the fact that it has 6 billion parameters.

A large language model (LLM) is a type of computational model designed for natural language processing tasks such as language generation. As language models, LLMs acquire these abilities by learning statistical relationships from vast amounts of text during a self-supervised and semi-supervised training process.

BookCorpus is a dataset consisting of the text of around 7,000 self-published books scraped from the indie ebook distribution website Smashwords. It was the main corpus used to train the initial GPT model by OpenAI, and has been used as training data for other early large language models including Google's BERT. The dataset consists of around 985 million words, and the books that comprise it span a range of genres, including romance, science fiction, and fantasy.

<span class="mw-page-title-main">PaLM</span> Large language model developed by Google

PaLM is a 540 billion-parameter transformer-based large language model (LLM) developed by Google AI. Researchers also trained smaller versions of PaLM to test the effects of model scale.

<span class="mw-page-title-main">Attention Is All You Need</span> 2017 research paper by Google

"Attention Is All You Need" is a 2017 landmark research paper in machine learning authored by eight scientists working at Google. The paper introduced a new deep learning architecture known as the transformer, based on the attention mechanism proposed in 2014 by Bahdanau et al. It is considered a foundational paper in modern artificial intelligence, as the transformer approach has become the main architecture of large language models like those based on GPT. At the time, the focus of the research was on improving Seq2seq techniques for machine translation, but the authors go further in the paper, foreseeing the technique's potential for other tasks like question answering and what is now known as multimodal Generative AI.

The XLNet was an autoregressive Transformer designed as an improvement over BERT, with 340M parameters and trained on 33 billion words. It was released on 19 June, 2019, under the Apache 2.0 license. It achieved state-of-the-art results on a variety of natural language processing tasks, including language modeling, question answering, and natural language inference.

OpenAI o1 is a generative pre-trained transformer. A preview of o1 was released by OpenAI on September 12, 2024. o1 spends time "thinking" before it answers, making it more effective in complex reasoning tasks, science and programming.

References

  1. ↑ "gpt-2". GitHub. Archived from the original on 11 March 2023. Retrieved 13 March 2023.
  2. ↑ Vaswani, Ashish; Shazeer, Noam; Parmar, Niki; Uszkoreit, Jakob; Jones, Llion; Gomez, Aidan N; Kaiser, Łukasz; Polosukhin, Illia (2017). "Attention is All you Need" (PDF). Advances in Neural Information Processing Systems. 30. Curran Associates, Inc.
  3. 1 2 3 4 5 6 7 8 9 10 11 12 13 Radford, Alec; Narasimhan, Karthik; Salimans, Tim; Sutskever, Ilya (11 June 2018). "Improving Language Understanding by Generative Pre-Training" (PDF). OpenAI. p. 12. Archived (PDF) from the original on 26 January 2021. Retrieved 23 January 2021.
  4. 1 2 "GPT-1 to GPT-4: Each of OpenAI's GPT Models Explained and Compared". 11 April 2023. Archived from the original on 2023-04-15. Retrieved 2023-04-29.
  5. 1 2 Tsvetkov, Yulia (22 June 2017). "Opportunities and Challenges in Working with Low-Resource Languages" (PDF). Carnegie Mellon University. Archived (PDF) from the original on 31 March 2020. Retrieved 23 January 2021.
  6. ↑ Zhu, Yukun; Kiros, Ryan; Zemel, Richard; Salakhutdinov, Ruslan; Urtasun, Raquel; Torralba, Antonio; Fidler, Sanja (22 June 2015). "Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books". arXiv: 1506.06724 [cs.CV]. # of books: 11,038 / # of sentences: 74,004,228 / # of words: 984,846,357 / mean # of words per sentence: 13 / median # of words per sentence: 11
  7. ↑ Williams, Adina; Nangia, Nikita; Bowman, Samuel (1 June 2018). "A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference" (PDF). Association for Computational Linguistics. Archived (PDF) from the original on 11 February 2020. Retrieved 23 January 2021. At 433k examples, this resource is one of the largest corpora available for natural language inference (a.k.a. recognizing textual entailment), [...] offering data from ten distinct genres of written and spoken English [...] while supplying an explicit setting for evaluating cross-genre domain adaptation.
  8. ↑ Lai, Guokun; Xie, Qizhe; Hanxiao, Liu; Yang, Yiming; Hovy, Eduard (15 April 2017). "RACE: Large-scale ReAding Comprehension Dataset From Examinations". arXiv: 1704.04683 [cs.CL].
  9. ↑ Mostafazadeh, Nasrin; Roth, Michael; Louis, Annie; Chambers, Nathanael; Allen, James F. (3 April 2017). "LSDSem 2017 Shared Task: The Story Cloze Test" (PDF). Association for Computational Linguistics. Archived (PDF) from the original on 22 November 2020. Retrieved 23 January 2021. The LSDSem'17 shared task is the Story Cloze Test, a new evaluation for story understanding and script learning. This test provides a system with a four-sentence story and two possible endings, and the system must choose the correct ending. Successful narrative understanding (getting closer to human performance of 100%) requires systems to link various levels of semantics to commonsense knowledge.
  10. ↑ Wang, Alex; Singh, Amanpreet; Michael, Julian; Hill, Felix; Levy, Omar; Bowman, Samuel R. (20 April 2018). "GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding". arXiv: 1804.07461 [cs.CL].
This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.