Deep Neural Networks for Web Page Information Extraction - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

Deep Neural Networks for Web Page Information Extraction

Tomas Gogar
  • Function : Author
  • PersonId : 1012055
Ondrej Hubacek
  • Function : Author
  • PersonId : 1012056
Jan Sedivy
  • Function : Author
  • PersonId : 1012057


Web wrappers are systems for extracting structured information from web pages. Currently, wrappers need to be adapted to a particular website template before they can start the extraction process. In this work we present a new method, which uses convolutional neural networks to learn a wrapper that can extract information from previously unseen templates. Therefore, this wrapper does not need any site-specific initialization and is able to extract information from a single web page. We also propose a method for spatial text encoding, which allows us to encode visual and textual content of a web page into a single neural net. The first experiments with product information extraction showed very promising results and suggest that this approach can lead to a general site-independent web wrapper.
Fichier principal
Vignette du fichier
430537_1_En_14_Chapter.pdf (1.48 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01557648 , version 1 (06-07-2017)





Tomas Gogar, Ondrej Hubacek, Jan Sedivy. Deep Neural Networks for Web Page Information Extraction. 12th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2016, Thessaloniki, Greece. pp.154-163, ⟨10.1007/978-3-319-44944-9_14⟩. ⟨hal-01557648⟩
841 View
3098 Download



Gmail Facebook Twitter LinkedIn More