- Amit Alfassy
- Assaf Arbelle
- et al.
- 2022
- NeurIPS 2022
Overview
Deep Search uses AI to collect, convert, curate, and ultimately search large document collections like public documents, such as patents and research papers. It makes information accessible that is too specific for common search tools to handle. It collects data from public, private, structured, and unstructured sources and leverages state-of-the-art AI methods to convert PDF documents into easily decipherable JSON format with a uniform schema that is ideal for today’s data scientists. It then applies dedicated natural language processing and computer vision machine-learning algorithms on these documents and ultimately creates searchable knowledge graphs.
Deep Search has already allowed scientists and businesses to search mountains of unstructured data for a while. In 2022, our team made deep search even more versatile and accessible with the release of Deep Search for Scientific Discovery (DS4SD), an open-source toolkit for scientific research and businesses.
Publications
- Oshri Naparstek
- Ophir Azulai
- et al.
- 2022
- KDD 2022
- Birgit Pfitzmann
- Christoph Auer
- et al.
- 2022
- KDD 2022
- 2022
- EMNLP 2022
- Sivan Harary
- Eli Schwartz
- et al.
- 2022
- CVPR 2022
- 2022
- CVPR 2022
- Girmaw Abebe Tadesse
- Celia Cintas
- et al.
- 2021
- AMIA Annual Symposium 2021
- Nikolaos Livathinos
- Cesar Berrospi
- et al.
- 2021
- IAAI 2021