Traditional handwritten text recognition (HTR) approaches ignore the multimodal characteristics of historical manuscripts. Moreover, they underestimate problems at the level of layout analysis, the detection of the logical reading order over a scanned page of text, and the recognition of textual and graphic patterns with a special meaning (headings, illuminated capitals, repetitive administrative forms, tables, and other markers). In order to exploit deep learning in these areas, it is necessary to have ‘humans in the loop’, who not only label characters and words and transcribe lines of text but also train the machine to analyse images in a multifaceted manner. The knowledge harvested in this manner is immediately usable to improve the recognition quality of traditional HTR algorithms.

We are looking for a highly motivated and qualified PhD student/researcher who will work towards developing new (machine learning and deep learning-based) algorithms and procedures that exploit human labelling and machine-based clustering efficiently. Human labelling (from Dutch cultural heritage partners) will address not only text but also other multimodal attributes of scanned text images (layout, graphics). The ultimate goal is to realize AI systems with a deep understanding of what a document is about.

The PhD researcher will work within the HAICu research project. HAICu (digital Humanities - Artificial Intelligence - Cultural heritage) project is a large-scale Dutch research project by universities and cultural-heritage institutions into new forms of Artificial Intelligence-based access to multimodal Cultural-Heritage data, both contemporary and historical. Within HAICu, AI researchers, Digital Humanities researchers, and a wide range of public and private partners will co-develop scientific solutions to unlock the true societal potential of the current heterogeneous digital heritage collections. It will provide easier, richer, and more reliable data access to citizens, journalists, civic organisations, and various other stakeholders.

Within the dynamic HAICu team, the PhD researcher will participate in Work Package 2, titled Continual Machine Learning and Humans in the Loop. In this Work Package, we will collaborate with digital humanities researchers from the University of Twente and partners from Dutch cultural heritage institutions, such as the Nationaal Archief, Collectie Overijssel, and Groninger Archieven.

In addition to publishing scientific articles, the researcher is expected to make the developed algorithms available to academic and institutional project partners under open-access conditions.

For more information about HAICu, please see https://www.haicu.science/

Founded in 1614, the University of Groningen enjoys an international reputation as a dynamic and innovative institution of higher education, offering high-quality teaching and research. Flexible study programmes and academic career opportunities in various disciplines encourage the 35,000 students and researchers alike to develop their talents. As one of the best research universities in Europe, the University of Groningen has joined forces with other top universities and networks worldwide to become a truly global center of knowledge.

Within the Faculty of Science and Engineering, the 4-year PhD position on digital humanities and cultural heritage is available at the Department of Artificial Intelligence, Bernoulli Institute. The candidate would become an active member of the HAICu project and work under the direct supervision of Dr. Maruf Dhali and Prof. Lambert Schomaker.

We are looking for an enthusiastic and talented PhD candidate with:

- a (research) master's degree (or equivalent) in Artificial Intelligence or Computer Science (or a related discipline with specialisation in machine learning or computer vision)
- good programming skills and hands-on experience with machine learning techniques and deep neural networks
- excellent problem-solving and analytical skills
- high motivation to work in multidisciplinary contexts
- an integrative and cooperative personality with excellent communication and social skills
- fluent proficiency in English – written and oral.

Fixed-term contract: 12 months.

We offer the following in accordance with the Collective Labour Agreement for Dutch Universities:

- a salary of €2,770 gross per month in the first year of the appointment, rising to €3,539 gross per month in the fourth year for a full-time position
- a holiday allowance of 8% of gross annual income and an 8.3% year-end bonus
- attractive secondary terms of employment. A favourable tax agreement, the ‘30% ruling’, may apply to non-Dutch applicants
- a full-time position (1.0 FTE). The successful candidate will first be offered a temporary position of one year. After a positive result and development interview, the contract will be extended for the remaining period of three years
- a PhD training programme is part of the agreement, and the successful candidate will be enrolled in the Graduate School of Science and Engineering.

Apart from your salary and employee status (no tuition fees) and an inspiring research environment, we offer you many fringe benefits:

- career services for partners of new employees moving to Groningen
- excellent work-life balance
- 232 holiday hours per year (based on full-time) and extra holidays between Christmas and 1 January
- a pension at ABP for which RuG pays the majority of the contribution
- multiple courses on topics such as time and stress management, mindfulness, academic writing, etc
- the possibility of following courses to learn Dutch
- help you settle down when you are moving from abroad.

Maruf Dhali, Assistant Professor in AI
m.a.dhali@rug.nl

Lambert Schomaker, Professor in AI
l.r.b.schomaker@rug.nl