Discriminative Adversarial Search for Abstractive Summarization (by Thomas Scialom)
Speaker: Thomas Scialom:
Twitter: https://twitter.com/ThomasScialom
◾ Talk Description
In this talk, Thomas Scialom will introduce a novel adversarial approach to improve beam search for sequence generation, and apply it to Abstractive Summarization: Discriminative Adversarial Search (DAS). Inspired by Generative Adversarial Networks (GANs), wherein a discriminator is used to improve the generator, our method differs from GANs in that the generator parameters are not updated at training time and the discriminator is only used to drive sequence generation at inference time.
Note: This paper was accepted at ICML 2020.
◾ Authors: Thomas Scialom, Paul-Alexis Dray, Sylvain Lamprier, Benjamin Piwowarski, Jacopo Staiano
◾ Link: https://arxiv.org/abs/2002.10375
◾ About dair.ai
Website: https://dair.ai/
GitHub: https://github.com/dair-ai
Twitter: https://twitter.com/dair_ai
Newsletter: https://dair.ai/newsletter/
Slack: https://join.slack.com/t/dairai/shared_invite/zt-dv2dwzj7-F9HT047jIGkunNKv88lQ~g
Видео Discriminative Adversarial Search for Abstractive Summarization (by Thomas Scialom) канала Elvis Saravia
Twitter: https://twitter.com/ThomasScialom
◾ Talk Description
In this talk, Thomas Scialom will introduce a novel adversarial approach to improve beam search for sequence generation, and apply it to Abstractive Summarization: Discriminative Adversarial Search (DAS). Inspired by Generative Adversarial Networks (GANs), wherein a discriminator is used to improve the generator, our method differs from GANs in that the generator parameters are not updated at training time and the discriminator is only used to drive sequence generation at inference time.
Note: This paper was accepted at ICML 2020.
◾ Authors: Thomas Scialom, Paul-Alexis Dray, Sylvain Lamprier, Benjamin Piwowarski, Jacopo Staiano
◾ Link: https://arxiv.org/abs/2002.10375
◾ About dair.ai
Website: https://dair.ai/
GitHub: https://github.com/dair-ai
Twitter: https://twitter.com/dair_ai
Newsletter: https://dair.ai/newsletter/
Slack: https://join.slack.com/t/dairai/shared_invite/zt-dv2dwzj7-F9HT047jIGkunNKv88lQ~g
Видео Discriminative Adversarial Search for Abstractive Summarization (by Thomas Scialom) канала Elvis Saravia
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Microsoft introduces Phi-3! #ai #llms #microsoft
Keep Learning ML (Session 1) | DSV, CompLex, Modern tools for emotions
Exploring Capabilities of Long-Context LLMs
Llama 3 is here! | First impressions and thoughts
Training an LLM to effectively use information retrieval
Question Understanding: COVID-Q: 1,600+ Questions about COVID-19
101 ways to solve search (by Pratik Bhavsar)
Best Practices and Lessons Learned on Synthetic Data for Language Models #ai #machinelearning #genai
TLDR Generation of Scientific Documents | ML Interview #1 with Isabel Cachola
Dive into Deep Learning (Study Group): Deep Learning Computation with PyTorch | Session 5
Understanding LLM Settings
State-of-the-art open-source LLM judges #ai #machinelearning #gpt4
Keep Learning ML #3 | Contrastively Trained Structured World Models
Learn about LLMs in this NEW course #ai #chatgpt #engineering
How I read and annotate ML papers![[LLM NEWS] AlphaFold 3, xLSTM, OpenAI's Model Spec, DeepSeek-V2, OpenDevin CodeAct 1.0](https://i.ytimg.com/vi/fzg84wDevkQ/default.jpg)
[LLM NEWS] AlphaFold 3, xLSTM, OpenAI's Model Spec, DeepSeek-V2, OpenDevin CodeAct 1.0
RAG Faithfulness #llms #ai #gpt4
Dive into Deep Learning (Study Group): Multilayer Perceptrons | Session 4
Reasoning with Intermediate Revision and Search with LLMs #chatgpt #ai #llms #science #programming
Dive into Deep Learning (Study Group): Modern CNNs | Session 7
SWE-Agent | An LLM-based Software Engineering Agent