Learning from similarity and information extraction from structured documents
share
Neural networks have successfully advanced in the task of information extraction from structured documents. In business document processing more precise techniques equal more automation and less manual work. In this paper we will design and examine various fully trainable approaches to use siamese networks, concepts of similarity, one-shot learning and context/memory awareness. The aim is to improve micro F_1 of per-word classification on a testing split of an existing real world document dataset. The results verify the hypothesis, that access to a similar (yet still different) page with it's target information improves the information extraction. Furthermore the added contributions (in addition to siamese networks) of employing a class information, query-answer attention module and skip connections to the similar page are all required to beat the previous results. Our best model improves previous state-of-art results by 0.0825 gain in F1 score. All the techniques used are not problem-specific and should be generalizable to help in other tasks and contexts. The code and anonymized version of the dataset are provided.
READ FULL TEXT