@inproceedings{arroyo-etal-2022-key,
    title = "Key Information Extraction in Purchase Documents using Deep Learning and Rule-based Corrections",
    author = "Arroyo, Roberto  and
      Yebes, Javier  and
      Mart{\'\i}nez, Elena  and
      Corrales, H{\'e}ctor  and
      Lorenzo, Javier",
    editor = "Chiticariu, Laura  and
      Goldberg, Yoav  and
      Hahn-Powell, Gus  and
      Morrison, Clayton T.  and
      Naik, Aakanksha  and
      Sharp, Rebecca  and
      Surdeanu, Mihai  and
      Valenzuela-Esc{\'a}rcega, Marco  and
      Noriega-Atala, Enrique",
    booktitle = "Proceedings of the First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning",
    month = oct,
    year = "2022",
    address = "Gyeongju, Republic of Korea",
    publisher = "International Conference on Computational Linguistics",
    url = "https://aclanthology.org/2022.pandl-1.2",
    pages = "11--20",
    abstract = "Deep Learning (DL) is dominating the fields of Natural Language Processing (NLP) and Computer Vision (CV) in the recent times. However, DL commonly relies on the availability of large data annotations, so other alternative or complementary pattern-based techniques can help to improve results. In this paper, we build upon Key Information Extraction (KIE) in purchase documents using both DL and rule-based corrections. Our system initially trusts on Optical Character Recognition (OCR) and text understanding based on entity tagging to identify purchase facts of interest (e.g., product codes, descriptions, quantities, or prices). These facts are then linked to a same product group, which is recognized by means of line detection and some grouping heuristics. Once these DL approaches are processed, we contribute several mechanisms consisting of rule-based corrections for improving the baseline DL predictions. We prove the enhancements provided by these rule-based corrections over the baseline DL results in the presented experiments for purchase documents from public and NielsenIQ datasets.",
}