Next Generation Search Technology
Our system solutions offer our clients a market advantage, we reduce their efforts in terms of time spent searching and reviewing information.
We are specialists in developing novel and innovative scientific knowledge management systems tailored to the needs of researchers and information search professionals. We provide unified platforms that can increase the productivity of industry and academia end-users, by exploring and implementing innovative text mining technologies.
Search Efficiency
We know how to help our customers find the relevant information and tailor it to the needs of our customers.
Development
We develop scientific knowledge management systems by exploring and implementing innovative text mining technologies.
Strategy
Our systems provide our customers with information and recomendations for purchase and research strategies.
WHAT WE OFFER
Artificial Intelligence Text Mining Consulting and Implementation
With our CEO Linda Andersson and her team, we can support you during the entire R&D process.
- Assessing the suitability of existing NLP services, Open-source software, and open access data to specific use cases .
- Designing system and components architecture.
- Establishing test and training data .
- Software components deliverables.
- Support through the entire deployment process with training for setting up cloud infrastructure or on-premises solutions to additional customized designed components .
Optimize and adapt your Natural Language Process and Deep Learning techniques
We offer a tailored training package to clients that develop their own customized AI text mining solutions. Take your text mining to the next level!
Read more...
Get started with your text mining development
We offer a hybrid package compose of training, support, and software deliverables. Designed for clients that are starting their journey on developing text mining tools.
Read more...
Ready to use API Rest Service and access to Artificial Researcher’s standard collections
Increase your knowledge discovery with Artificial Researcher’s products and services. Free training included!
Read more...
Get your complete information retrieval system with the Artificial Researcher Data pipeline solution
Increase your knowledge discovery with Artificial Researcher’s products and services. We process client data
Read more...
Products and Services
Data Pipeline Solution
The Artificial Researcher Data Pipeline solution is a scalable and complete solution that process client machine-readable text data through a text mining process flow.
The Data Pipeline generates sustainable ready to use indices and ontologies, as well as enhanced data formats, which can be integrated into client’s own Information Retrieval system. By integrating domain ontologies into the information retrieval system, the AR technology provides automatic query expansions with understandable semantic information (Transparent AI). For easy deployment, the indices and ontologies can be packages together with Artificial Researcher Ontology Service and the Artificial Researcher Passage Retrieval Service.
Ontology Service
The Artificial Researcher Ontology Service is a domain-specific ontology population service. The service utilizes the AR NLP-toolkit for automatic term recognition to extract single words and phrases by combining NLP and gazetteers with a domain-specific trained BERT model.
The AR Ontology Service is offered as a SaaS or on-premises software which allow direct access to through a built-in rest API. The service can also be accessed by utilizing AR Graph Search Service or desktop client.
To try the AR Ontology Service, use the API key <b10225791d2a478c9ff3d8cd106ad65a> - DEMO
An alpha demo is available on the link.
Graph Search Service
The novel Artificial Researcher Graph Search Service visualise domain-specific ontologies extracted from several collections. To provide easy knowledge and terminology discovery, the extracted terms are directly linked to text paragraphs and connected to domain classification as well as taxonomy. AR Graph Search Service explores automatic generated ontology and passage (paragraph) retrieval. The term and related concepts are extracted using unsupervised methods combining NLP and deep learning. By integrating domain-specific ontologies into the information retrieval system, the AR technology provides automatic query expansions with understandable semantic information to provide Transparent Artificial Intelligence (AI).
To try the AR Graph Search Service, use the API key:
<b10225791d2a478c9ff3d8cd106ad65a> - DEMO
An alpha demo is available on the link.
Passage Retrieval Service
The Artificial Researcher Passage Retrieval Service uses innovative text mining technologies based on 15 years of collected know-how and research that gives you state of the art machine learning. The AR Passage Retrieval Service service offers a unique and user-friendly opportunity to search in different scientific domains, using a text segment as input, which can be combined with bibliographic meta-data filters.
The data collections available to you in this demo are: COVID-19 Open Research Dataset (CORD-19) data set, a sample set from the EP Full-Text Data for Text Analytics, and a sample composed of different scientific publications within technical and medical science provided by CORE.uk (Science).
For access to our larger collections, which we provide via a APIs, book a meeting.
NLP-toolkit Services
The Artificial Researcher NLP-toolkit Services provide the industry and academia with a set of Natural Language Processing (NLP) tools. The toolkit contains for example domain-specific trained DL models, terminology detection, PICO and dataset name extraction, as well as domain document classification.
NLP-toolkit Services can be access via a rest API. NLP-toolkit Services is offered as SaaS or on-premises software.
Events
For information about our online events, demos, workshops and conferences follow us on LinkedIn link
Previous Events
Legal Tech für Alle - November 16, 2021
At“Legal Tech für ALLE!”, link, our CEO Linda Andersson will present the technology and the design behind Artificial Researcher text mining software and the SaaS text mining pipeline - Artificial Research Data Pipeline solution. To visualize the search software produced by the AR Data Pipeline solution, we have developed an innovative Graph Search service. You can try out the demo to access terms with the International Patent Classification and Medical Subject Headings (MeSH) link
Artificial Researcher co-organized the workshop series on Patent Text Mining and Semantic Technologies 2021 on July 15, for more info visit PatentSemTech (tuwien.ac.at)
PatentSemTech’21 workshop was held as a full-day online event in conjunction with SIGIR 2021, SIGIR 2021
Projects and Partners
iFAIR
Partners
Research Studios Austria FG - website
Supported by European Open Science Cloud - website
Project
iFAIR: Identifying datasets by mining research papers to make more data FAIR
FAIR research data shall be Findable, Accessible, Interoperable, and Reusable.
This co-creation project aims to develop a new proof-of-concept technology for automatic identification of datasets by mining research publications. More specifically, we aim to improve the current open source state-of-the-art tool GROBID (grobid.readthedocs.io) for parsing raw research papers.
This work will contribute to closing the gap between datasets that are mentioned but never properly registered. For instance, our tool will make it possible to:
- Analyse and monitor the proportion of datasets mentioned in scientific papers but are not yet FAIR.
- Develop tools to notify authors of scientific papers containing references to non-FAIR datasets, and of the need to make these datasets FAIR. This could be then connected to services helping to find an appropriate data repository, such as re3data.org.
The work in this project will find its use in the processing pipelines of tools creating research graphs, scholarly search engines, open repository systems, publishing systems, etc., and will support the needs of researchers and students by contributing to making research datasets more discoverable.
Artificial Researcher - Ontology for Covid-19
Partners
Supported by European Open Science Cloud - website
Project
AR-Onto-Covid: A Knowledge-Based Resource for Covid-19
In the current crisis of the Covid-19 pandemic we focus our expertise on the development of novel and innovative scientific knowledge management systems that cater to the global needs of researchers and information search professionals. We reduce their effort in terms of time spent searching for information and reviewing publications, making it possible for researches and medical professionals to intensify the work on the development of vaccines and treatments.
By combining our expertise in Natural Language Processing and Artificial Intelligence/Machine Learning with human expert annotations we create high-quality knowledge-based resources starting from the openly available Covid-19 resources. At the end of this project we will have provided a benchmark data set that can be used for further Machine Learning experiments, together with an Covid-19 ontology and an API-based solution to query it.
In this project we develop a solution that increases access to the medical knowledge published as Open Access, as well as to the relevant bio-medical patent documents. Our solution will make the bio-medical data related to Covid-19 freely searchable and openly available to the EOSC community and researchers at large.
Artificial Researcher in Science
Partners
Technische Universität Wien IFS - website
Technische Universität Wien Bibliothek - website
Supported by Vienna Business Agency - website
Project
Artificial Research in Science: Efficient Scientific Publication Mining (AR-Science)
In the project AR-Science we aim to develop a novel and innovative platform, which automatically handles scientific information needs and presents the information to the users according to their requests. The result of this work will be a software prototype that, after passing series of user testing conducted by the TU WIEN Library (UB TU), will be commercialised by the start-up AR-IT. The AR-Science prototype has a two-year development cycle since this is a collaboration with TUW University Library and TUW IFS. The AR-Science solution is a significant long-term commitment and investment for the academic libraries
Artificial Researcher in Open Access
Partners
Supported by Austria Wirtschaftservice - website
Project
Artificial Researcher in Open Access (AR-OpenAccess)
With AR-OpenAccess we give institutions the possibility to test and evaluate our technical solution before they agree to a commitment. The AR-OpenAccess solution is similar to the AR-Science solution and will automatically handle information needs and present the information to the users according to their requests. By first introducing the AR-OpenAccess for demos and test trial to the research community – we can reach more universities and libraries worldwide.
This project is completed - please contact us for more information.
Innovative Design
What makes our solution innovative?
Within our product and services, we explore a new text mining technology to retrieve scientific publications better fitted to the information needs of students and researchers.
Part of the text mining technology was develop during our CEO Linda Andersson's PhD work at Technical University of Vienna (TU Wien), the paragraph retrieval, the automatic query formulation, and a merging method of document index and paragraph index.
The traditional search technology requires keywords, however, keywords are a limited representation of information needs. The future scientific knowledge management system ought to be a dialogue between the user and the system, requiring integration of language, scientific domain knowledge, and understanding of user information needs. Instead of requiring the user to convert her information need into a set of keywords, the system should aid the user to represent the information need on a conceptual level by means of user contexts. The text mining research must go towards categorizing the information needs and sub discipline of scientific fields. We argue that, by integrating an eLearning system and combining the benefits of supervised learning with reinforcement learning, we obtain partly self-learned annotated data that will boost the efficiency of customized solutions for each specific information need, and, at the same time, will provide users with added knowledge values
What is our solution technology?
The AR-Science software is integrated into the libraries existing system as an add- on and hosted on the libraries infrastructure. We provide the services of indexing in-house, open access, as well as closed access if the library has the text mining permission in the contract with the information providers. Our solution does not require full-text storage, only a digital fingerprint is stored, and the in-house and the closed publication indices, as well as the usage information is owned and hosted by the library. We provide services in terms of maintenance, index update, functionalities update and optimization - i.e. we make the searching different type of resources more time efficient for students and researchers, but the libraries have the control of the data resources storage and the usage information. AR-Science provide more precise usage information in comparison with COUNTER standard. For example, the libraries have access to search statistics such as open access versus closed publications for each specific scientific field
© Copyright Artificial Researcher – IT GmbH
Handelsgericht Wien
FN 505425y
Wirtschaftskammer Wien
UST/VAT: ATU74181725