Knowledge exploration for scientific discovery

Deep Search

Knowledge exploration for scientific discovery

Information is locked in PDFs, papers, and patents. Deep Search allows users to explore public and proprietary documents with ease.
Interface screenshotInterface screenshot

Ingest, structure, explore

Deep Search uses state-of-the-art AI to convert, search, and make use of information fragmented across organizations and the public domain.

Convert documents into structured files

High quality, with no user intervention. Upload and forget

Search proprietary and public data
Search patents in the organic-chemistry domain

Natural language processing to ingest and analyze data

Deep Search imports and analyzes data from public, private, structured, and unstructured sources such as journal articles, patents, or technical reports. AI then breaks down the data and classifies it into fundamental parts. After reviewing unstructured data, the model classifies all documents into their fundamental parts. By using this AI model and NLP (Natural Language Processing), Deep Search is able to ingest and understand large collections of documents and unstructured data at scale. Once the data has been consolidated and extracted, Deep Search organizes and structures it into a searchable knowledge graph — enabling users to robustly explore information extracted from tens of thousands of documents without having to read a single paper.

Accelerating materials discovery using artificial intelligence, high performance computing and robotics.EO Pyzer-Knapp, JW Pitera, PWJ Staar, S Takeda, T Laino, DP Sanders, … npj Computational Materials 8 (1), 1-9
DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis.B Pfitzmann, C Auer, M Dolfi, AS Nassar, PWJ Staar. arXiv preprint arXiv:2206.01062
TableFormer: Table Structure Understanding with Transformers.A Nassar, N Livathinos, M Lysak, P Staar Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. arXiv preprint arXiv:2203.01017
Delivering Document Conversion as a Cloud Service with High Throughput and Responsiveness.C Auer, M Dolfi, A Carvalho, CB Ramis, PWJ StaararXiv preprint arXiv:2206.00785
Robust PDF document conversion using recurrent neural networks.N Livathinos, C Berrospi, M Lysak, V Kuropiatnyk, A Nassar, A Carvalho, ... Proceedings of the AAAI Conference on Artificial Intelligence 35 (17), 15137

Put Deep Search to work

Full document conversion

Information from PDF text, tables, charts, and images is parsed and assembled into a JSON file for further use or export

Securely search proprietary and public data

Upload your own documents, or search millions of pre-loaded technical documents from the public domain, including Patents, News, and Open-Access Publications

Prepare data for downstream use

Enrich converted documents with detected entities and related statistics and their units

Multi-modal access

Third-party data sources made available to tune models on specific chemistry domains

Try now, for free

Unlock data from proprietary and public sources today with Deep Search, risk-free.

Deep Search for Teams

Deep Search is most powerful when used by your entire team. Request a meeting to learn more.