How to Leverage Document AI to Simplify People’s Financial Lives?
About This Video
Documents are a principal part of our day to day finance management. Accessing and extracting the data embedded in documents has become one of the most highly sought-after technologies in many sectors, including financial services, real estate, insurance, government, legal, and healthcare. A central goal shared among these sectors is automating document processing to extract the documents’ fundamental structured information and instantly delivering that information when needed . Documents for which this goal is relevant include financial documents (such as receipts, invoices, contracts, mortgage documents, loan applications, and purchase orders), government documents (such as tax forms, licenses, and certificates), and many more. Manual extraction of information from documents could take 3-5 minutes depending on the amount of key information and the complexity of the document. Without automation, the amount of manual work for document intensive tasks – such as medical case review, evidence processing, tax preparation, small business account etc – can add up to many hours. The primary challenge to extraction of information in such documents is that embedded data can be present in a combination of unstructured text; semi-structured content, such as multi-column formats, tables, and key-value pairs; and graphical content, such as figures and vector graphics. The general ability to understand and interpret documents’ various presentations of data is a critical and challenging application of artificial intelligence (AI). In this workshop we will share the SoTA of document intelligence techniques and how it is evolving in the generative AI era.
In This Video
Data Science Group Manager, Intuit
Shir Meir Lador is the data science manager of the document intelligence group at Intuit, a global leader in the industry of financial management software. Shir is the co-founder of PyData Tel Aviv meetups, WiDS Tel Aviv ambassador, the co-host of “Unsupervised” (a podcast about data science in Israel), and gives talks at various machine learning and data science conferences and meetups. Shir holds an M.Sc. in electrical engineering and computers with a major in machine learning and signal processing from Ben-Gurion University.
Principal Data Scientist, Intuit
Joy Rimchala is a Principal Data Scientist in the Document Intelligence group and at Intuit leading the research and innovation on AI driven document services. Joy’s current focus is to scale and enhance AI first document intelligence capabilities across Intuit – e.g. enabling document intelligence modeling in low resource settings and knowledge-enhanced document intelligence across Intuit’s products and expert platforms. Joy’s current area of interests includes the use of generative AI combined with domain knowledge to enhance document intelligence models. Joy was one of the organizers of KDD 2018 XAI workshop and serves as a program committee and a reviewer at leading conferences including ACL, EACL, EMNLP, and AACL-IJCNLP. Joy holds a PhD in Biological Engineering from MIT with a focus on developing parameter estimation methods in modeling cell decision as a Markov process.