Tree positional encodings for transformer models on HTML DOM tree element classification : Enabling structurally aware transformer models through positional encodings to improve performance on an HTML element classification problem

Tree positional encodings for transformer models on HTML DOM tree element classification : Enabling structurally aware transformer models through positional encodings to improve performance on an HTML element classification problem

With the continued proliferation of access and the usage of the internet, the field of web learning is continuously growing in order to automate and improve parts of our experience on the web. Research in web learning has often lagged behind its counterparts in Natural Language Processing (NLP), nov...

Full description

Bibliographic Details
Main Author: Rousselet, Gustave
Format: Others
Language:English
Published: KTH, Skolan för elektroteknik och datavetenskap (EECS) 2021
Subjects:
Transformer
Positional Encoding
HTML
DOM
Tree
Element
Positionskodning
Träd
Computer and Information Sciences
Data- och informationsvetenskap
Online Access:http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-305138

Internet

http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-305138

Similar Items