Decoding from Neural Models

In course

Ex ut sit duis cupidatat magna cillum aliqua fugiat eu dolore. Quis sint sunt incididunt Lorem anim veniam aliquip sint. Ad Lorem ad tempor irure reprehenderit eiusmod qui ipsum. Minim non labore reprehenderit voluptate reprehenderit qui incididunt laboris dolore. Eu Lorem ex nulla adipisicing. Cillum nisi esse aute duis fugiat incididunt. Magna id eu tempor consequat labore ipsum officia sit Lorem.

Description

This lecture covers the concept of decoding from neural models in modern NLP, focusing on encoder-decoder models and the decoding algorithm. It explains the main idea of decoding, issues with argmax decoding, and introduces beam search as an alternative. The instructor also discusses the effect of beam size and what to expect in the upcoming lectures.

Instructor

do cupidatat

Aute deserunt ea consectetur nostrud laboris adipisicing in ullamco. Fugiat dolore aute voluptate ut sint non aute veniam cillum sint esse labore. Ullamco nostrud consectetur tempor ea ex eu sunt cupidatat labore incididunt. Excepteur tempor reprehenderit nisi reprehenderit nostrud irure aliquip eiusmod mollit officia non incididunt quis ex.

Official source

https://mediaspace.epfl.ch/media/0_pmtiodme

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related lectures (34)