Recurrent Neural Network Approach for Table Field Extraction in Business Documents - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Recurrent Neural Network Approach for Table Field Extraction in Business Documents

Réseaux de neurones récurrents pour l’extraction de champs de tableau dans des documents d’entreprise

Alex Aussem
Haytham Elghazel
Jérémy Espinas
  • Fonction : Auteur
  • PersonId : 937824

Résumé

Efficiently extracting information from documents issued by their partners is crucial for companies that face huge daily document flows. Particularly, tables contain most valuable information of business documents. However, their contents are challenging to automatically parse as tables from industrial contexts may have complex and ambiguous physical structure. Bypassing their structure recognition, we propose a generic method for end-to-end table field extraction that starts with the sequence of document tokens segmented by an OCR engine and directly tags each token with one of the possible field types. Similar to the state-of-the-art methods for non-tabular field extraction, our approach resorts to a token level recurrent neural network combining spatial and textual features. We empirically assess the effectiveness of recurrent connections for our task by comparing our method with a baseline feedforward network having local context knowledge added to its inputs. We train and evaluate both approaches on a dataset of 28,570 purchase orders to retrieve the ID numbers and quantities of the ordered products. Our method outperforms the baseline with micro F1 score on unknown document layouts of 0.821 compared to 0.764.
Fichier principal
Vignette du fichier
paper_certified_by_IEEE_PDF_eXpress.pdf (674.2 Ko) Télécharger le fichier
conference_poster.pdf (519.76 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02156269 , version 1 (15-07-2019)

Identifiants

Citer

Clément Sage, Alex Aussem, Haytham Elghazel, Véronique Eglin, Jérémy Espinas. Recurrent Neural Network Approach for Table Field Extraction in Business Documents. 15th International Conference on Document Analysis and Recognition (ICDAR 2019), Sep 2019, Sydney, Australia. ⟨10.1109/ICDAR.2019.00211⟩. ⟨hal-02156269⟩
495 Consultations
1709 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More