The Conference for Machine Learning Innovation

Multi Tasking Deep Learning for Natural Language Processing – Transfer Learning

Session
Join the ML Revolution!
Register until the conference starts:
✓ 2-in-1 conference special
✓ 10 % Team Discount
Register Now
Join the ML Revolution!
Register until the conference starts:
✓ 2-in-1 conference special
✓ 10 % Team Discount
Register Now
Join the ML Revolution!
Register until August 12:
✓ML Intro Day for free
✓Save up to $380
Register Now
Join the ML Revolution!
Register until August 12:
✓ML Intro Day for free
✓Save up to $380
Register Now
Join the ML Revolution!
Register until November 7th:
✓Save up to € 210
✓10% Team Discount
Register Now
Join the ML Revolution!
Register until November 7th:
✓Save up to € 210
✓10% Team Discount
Register Now
Infos

In this talk, we will cover how to model model different natural language processing. In present NLP tasks like word-based or sentence-based classification, sentence generation and question answering, it is a challenge to train models with little domain information. The key solution is using a pre-trained model and transfer learn. BERT from google and MTDNN from Microsoft have been breaking all set benchmarks in recent years. Understanding how to use transfer learning and multi tasking is key in building a model for the task. In this talk, we will discuss different models like ULMFIT, GPT and BERT, which are popular for transfer learning, and then we will analyze how multi tasking can immensely improve this task and different ways of doing multi tasking.

This Session originates from the archive of Diese Session stammt aus dem Archiv von SingaporeSingapore . Take me to the program of . Hier geht es zum aktuellen Programm von Munich Munich .

This Session originates from the archive of Diese Session stammt aus dem Archiv von SingaporeSingapore . Take me to the program of . Hier geht es zum aktuellen Programm von Singapore Singapore .

This Session originates from the archive of Diese Session stammt aus dem Archiv von SingaporeSingapore . Take me to the program of . Hier geht es zum aktuellen Programm von Berlin Berlin .

This Session Diese Session originates from the archive of stammt aus dem Archiv von SingaporeSingapore . Take me to the current program of . Hier geht es zum aktuellen Programm von Munich Munich , Singapore Singapore or oder Berlin Berlin .

Behind the Tracks