From Structured Document To Structured Knowledge

Structured documents, such as scientific literature and medical records, are rich resources of knowledge. However, most natural language processing techniques treat these documents as plain text, neglecting the significance of layout structure and visual signals. Modeling such structures is essentia...

Full description

Bibliographic Details
Main Author: Qian, Yujie
Other Authors: Barzilay, Regina
Format: Thesis
Published: Massachusetts Institute of Technology 2023
Online Access:https://hdl.handle.net/1721.1/151225