Speaker: Martin Andrews
This talk will explain a major current trend in Natural Language Processing : the increasing focus on using pre-built 'pure' language models (such as ELMO or the model recently announced by OpenAI), and then fine-tuning the output to suit your application. Martin will explain how this works, and you can create better models for your data, leveraging the models created on other, huge datasets by Google / OpenAI / Facebook / etc.
Produced by Engineers.SG
Help us caption & translate this video!