Lecture

Graph-to-Graph Transformers: Syntax-aware Graph Encoding

In course

Sint irure ex amet nostrud excepteur ad excepteur ea sunt consectetur sit. Laborum enim nisi do mollit. Dolor dolore officia ut adipisicing ullamco. Culpa qui nulla sint elit nisi aliqua enim veniam incididunt eu quis non.

Description

This lecture covers the Syntax-aware Graph-to-Graph Transformer architecture, which improves the input of graph relations into the self-attention mechanism of the Transformer model. It enables effective conditioning on syntactic dependency graphs for predicting both dependency-based and span-based semantic role labelling graphs.

Instructor

qui et deserunt quis

Ipsum ad pariatur ut do eiusmod anim sit exercitation. Ea cupidatat cupidatat do consequat consequat. Laboris dolor fugiat laboris ipsum ullamco voluptate consectetur commodo mollit ipsum et tempor laboris. Occaecat consequat fugiat aliqua anim officia mollit id irure occaecat.

Official source

https://mediaspace.epfl.ch/media/0_z5ycx4w8

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.

Ontological neighbourhood

Information engineering

Machine learning: Artificial neural networks

Natural language processing: Topics in natural language processing

Mathematics

Discrete mathematics: Graph theory

Related lectures (67)

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.