NEW (07/12/2021): The second edition of Document Intelligence (DI) Workshop is organized with KDD 2021. Workshop will be held on Sunday August 15, 2021. Check out the list of accepted papers and the workshop schedule.
Note: This website represents the First Workshop on Document Intelligence with NeuriPS 2019.
NEW (12/10/2020): The Report of the Document Intelligence (DI) 2019 Workshop is published in December 2020 Edition of SIGKDD EXPLORATIONS , and available here:
NEW (12/15/2019): The video recording of Document Intelligence Workshop presentations is available below:
NEW (12/1): The Best Paper Award of the DI'2019 Workshop goes to paper entitled “BERTGrid: Contextualized Embedding for 2D Document Representation and Understanding”, by Timo I. Denk and Christian Reisswig.
Business documents are central to the operation of business. Such documents include sales agreements, vendor contracts, mortgage terms, loan applications, purchase orders, invoices, financial statements, employment agreements and a wide many more. The information in such business documents is presented in natural language, and can be organized in a variety of ways from straight text, multi-column formats, and a wide variety of tables. Understanding these documents is made challenging due to inconsistent formats, poor quality scans and OCR, internal cross references, and complex document structure. Furthermore, these documents often reflect complex legal agreements and reference, explicitly or implicitly, regulations, legislation, case law and standard business practices.
The ability to read, understand and interpret business documents, collectively referred to as “Document Intelligence”, is a critical and challenging application of artificial intelligence (AI) in business. While a variety of research has advanced the fundamentals of document understanding, the majority have focused on documents found on the web which fail to capture the complexity of analysis and types of understanding needed across business documents. Realizing the vision of Document Intelligence remains a research challenge that requires a multi-disciplinary perspective spanning not only natural language processing and understanding, but also computer vision, knowledge representation and reasoning, information retrieval, and more -- all of which have been profoundly impacted and advanced by neural network-based approaches and deep learning in the last few years.
The goal of DI 2019 Workshop is to bring together AI researchers, academics and industry practitioners to discuss the opportunities and challenges for Document Intelligence. The workshop will be a 1-day workshop consisting of presentations by invited speakers on research, academic and industry challenges and recent progress in Document Intelligence topic. The workshop will embrace open discussions in form of breakout sessions and/or panel discussions reflecting on the major challenges in Document Intelligence, as well as a poster session for presenting the accepted peer-reviewed papers.
Call For Papers
Paper Submission Deadline:
September 9, 2019 (Extended): Friday, September 13th23:59:59 AOE (Saturday, September 14th, 11:59:59 a.ma. GMT).
Paper Notification Date: October 1, 2019
Workshop Date: December 14, 2019
Tania Bedrax Weiss is a Senior Staff Research Scientist at Google. Her current focus is on identifying untapped problems in Natural Language Understanding at Google and outlining research agendas to advance the state-of-the-art. In particular, she’s been focusing on Natural Language powered Recommendations, Language Grounding, and Pragmatics. During the 13+ years she’s been at Google she has launched transformative products in Google Play, Ads, and Search. Previously, she worked at NASA Ames Research Center and was part of the team that wrote the software used to schedule daily observations for Spirit and Opportunity. She has also worked in industry on automated configuration and pricing systems. She holds a PhD from the University of Oregon in Artificial Intelligence.
Paul Bennett is the Principal Research Manager of the Information & Data Sciences group in Microsoft Research AI. His published research has focused on a variety of topics surrounding the use of machine learning in information retrieval – including ensemble methods and the combination of information sources, calibration, consensus methods for noisy supervision labels, active learning and evaluation, supervised classification and ranking, crowdsourcing, behavioral modeling and analysis, and personalization. Some of his work has been recognized with awards at SIGIR, CHI, and ACM UMAP, and ECIR. He has been an invited speaker at multiple NeurIPS workshops in the past and is serving on the NeurIPS 2019 PC. He has experience organizing a variety of conferences and workshops including: PC Co-Chair WSDM 2019, General Co-Chair WSDM 2016, ICML 2013 Workshop on Crowdsourcing, and the KDD 2009 Workshop on Human Computation. He has shipped machine learning based-methods in products such as Bing document understanding, Bing ranking, Bing personalization, Cortana, and Office. Prior to joining MSR in 2006, he completed his dissertation in the Computer Science Department at Carnegie Mellon with Jaime Carbonell and John Lafferty. While at CMU, he also acted as the Chief Learning Architect on the RADAR project from 2005-2006 while a postdoctoral fellow in the Language Technologies Institute.
Nigel Duffy is a technologist and entrepreneur serving as the Global AI Leader for EY (Ernst & Young). EY is a global professional services firm of more than 270,000 people operating in more than 150 countries. At EY Nigel leads a global team of AI scientists and engineers working to transform EY with a particular focus on the reading and interpretation of business documents. Prior to EY he served as CTO of Sentient Technologies, where he led the research, and development of Sentient’s Artificial Intelligence technologies, and their application to equity trading, online retail, and website optimization. Nigel was previously the co-founder and CTO at Numerate Inc. where he invented technologies which rapidly and repeatedly designed novel drug candidates for diseases including cancer, hepatitis C, HIV, and heart disease. Prior to this he was VP of Engineering at Pharmix and worked as a research scientist at AiLive, developer of the Wii Motion Plus. Nigel has also spent time at Amazon A9 working on tools for large scale analytics in product search. Nigel's PhD is from UC Santa Cruz where his original research included the first theoretical papers on gradient boosting, early work on kernel methods for natural language, and some of the first applications of machine learning to gene expression arrays. Nigel has a master’s degree in mathematics and bachelor’s in mathematics and computer science from University College Dublin where he worked on Boltzmann machines and energy based methods for computer vision. Nigel original work includes papers in Machine Learning, Chemistry, Biology, Linguistics, and Economics. He holds patents or patent applications in drug design, computer games, pharmaceutical compounds, online retail, computer vision, and automatic machine learning.
Rama Akkiraju is an IBM Fellow, Master Inventor and IBM Academy Member, and a Director, at IBM’s Watson Division where she leads the AI operations team with a mission to scale AI for Enterprises. Rama also heads the AI mission of enabling natural, personalized and compassionate conversations between computers and humans. Rama has been named by Forbes as one of the ‘Top 20 Women in AI Research’ in May 2017, has been featured in ‘A-Team in AI’ by Fortune magazine in July 2018 and named ‘Top 10 pioneering women in AI and Machine Learning’ by Enterprise Management 360. Rama has co-authored 4 book chapters, and over 100 technical papers. Rama has 18 issued patents and 25+ pending. She is the recipient of 3 best paper awards in AI and Operations Research. Rama holds a Masters degree in Computer Science and has received a gold medal from New York University for her MBA for highest academic excellence. Rama served as the President for ISSIP, a Service Science professional society for 2018 and continues to actively drive AI projects through this professional society. Rama has chaired and organized various workshops in the past at IEEE and INFORMs conferences. Most recently. Rama had organized a workshop and a panel on ‘AI and Biases’ at HICSS 2019 Hawaii International Conference on System Sciences in January 2019.
Technical Program Committee Chair
Hamid Motahari is Head of AI Research and a Principal AI Scientist at the EY AI Lab where he is leading a team of AI scientists in text and document understanding. Prior to joining EY Hamid was the Research Lead for Cognitive Solutions at IBM Research, and a member of IBM Academy of Technology, where his focus was on cognitive technologies, document understanding and conversation understanding. He was a lead for a Global Technology Outlook topic on Cognitive Business Processes in 2016, and his work have contributed and impacted various products in enterprise software, Watson and IT and professional services within IBM, for which he has received numerous research recognition, and research impact awards. Hamid holds a Visiting Research Fellow position at the Computer Science and Engineering School at the University of New South Wales, Australia where he is co-supervising graduate students. He is a Senior Member of IEEE, and has published 100+ scholarly papers in various conferences in AI, Web, IT Services, and IEEE/ACM journals. Hamid has chaired and organized various conferences and workshops in the past IEEE, ACM, AAAI and INFORMS conferences.