The Institute for Logic, Language and Computation (ILLC) is a renowned research institute at the University of Amsterdam, in which researchers from the Faculty of Humanities and the Faculty of Science collaborate. The research carried out at Humanities forms one of the six research schools within this faculty. ILLC’s central research area is the study of fundamental principles of encoding, transmission and comprehension of information. Research at ILLC is interdisciplinary, and aims at bringing together insights from various disciplines concerned with information and information processing, such as logic, philosophy, linguistics, musicology, mathematics, computer science, artificial intelligence and cognitive science.
The ILLC is looking to fill one position for a postdoc in Computational Linguistics in Arianna Betti’s group Concepts in Motion within e-Ideas (2017-2022, VICI), a project funded by the Netherlands Organisation for Scientific Research (NWO) and directed by Arianna Betti (Principal Investigator). The project is carried out by a team of computational experts, and experts in history and philosophy of logic, mathematics and biology. We aim at developing a groundbreaking, new computational methodology to trace how concepts change in historical corpora from 1749-1940 in English, German, and Polish. The corpus is of extreme conceptual density and rather small from a computational perspective (about 240.000 pages in total) but big from a philosophical one, and includes works by Wolff, Kant, Bolzano, Frege, Russell and Quine. We want to use a mix of top-down and bottom-up approaches: from the humanities point of view we plan to rely on a scholarly sound method in intellectual history that we have developed ourselves (the ‘model approach’ to the history of ideas), and from the computational point of view on an ontology approach coupled with distributional semantics.
A short description of the project can be found here. A full description of the project is available on request.
The Concepts in Motion group has conducted pioneering work in applying computational tools to the history of philosophy since 2009, has extensive experience with all aspects of the typical workflow of philosophers going computational (including OCR challenges, issues in corpus-selection and high quality corpus-building), and is familiar both with information retrieval approaches from computer science and word embedding approaches from computational linguistics. The group has strong, actual collaborative links to the Benelux Digital Humanities community, and to Dutch computer science groups in knowledge representation (Frank van Harmelen, VU), computational linguistics (Piek Vossen, VU) and visualisation and geometrical algorithmics (Bettina Speckmann, Eindhoven). The PI is a member of the Network Institute (NI) of VU University, a major player in the field of digital humanities in the Amsterdam area and the Netherlands, and has an extensive international network of experts in history and philosophy of logic, historical NLP, library and information sciences, and visualization in the Humanities.
Computational Linguistics Embedding. The project’s host ILLC is home to a leading research group in Computational Linguistics with a long history in statistical natural language processing since the early 1990s. Current research includes computational and digital humanities (Rens Bod), probabilistic parsing and grammar induction (Tejaswini Deoskar), computational pragmatics and dialogue modelling (Raquel Fernández), information retrieval (Jaap Kamps), statistical morpho-syntactic parsing and machine translation (Khalil Sima’an), optimality theory and discourse (Henk Zeevat), and computational cognitive science (Willem Zuidema). The group organises a regular CL seminar.
Project description
We are looking for a postdoctoral researcher in computational linguistics to carry out the computational research required by the project. The postdoc will be aided by a scientific programmer for tool implementation. Both will work in close cooperation within a team with a strongly methodological attitude and experience with interdisciplinary work and computational tools, which will include the PI and three other philosophers as domain experts (Arianna Betti, 19-20th century history and philosophy of logic focusing on the concept of consequence; Hein van den Berg, 18th century history and philosophy of biology focusing on the concept of life; and one postdoc and one phd researcher to be hired in 19th century history and philosophy of logic and mathematics, focusing on consequence and plurality). We aim at a constant and truly interdisciplinary interaction between philosophical interpretation, construction and calibration of the tools and the computational exploration of the data.
Although the focus of the project is in adapting and calibrating existing technologies, rather than developing new ones, the project presents several technically and methodologically challenging aspects. The main challenge will be constructing a methodology that can reach a level of subtlety and saliency of analysis helpful to philosophers. First, the domain has an essential focus on extremely fine-grained nuances of meaning and great amount of subtle variation in small historical corpora with likely OCR problems, and requires author-specific lexical semantics at a much more fine-grained level than usually done. This will require experimenting with new distributional semantics and vector models for the type of texts at issue. Second, the application of a mix of top-down (semantic modelling based on ontologies) and bottom-up approaches relying on distributional semantics techniques forces the computational extraction of concepts/relations to happen within a complex, general and coherent conceptual architecture: the latter needs to be sensibly connected to the lexical level of the text (a topical challenge at the interface of AI and NLP).
The ideal candidate for the job has a PhD in computational linguistics, experience with working in teams comprising experts in text-based humanities and with the typical challenges of the field, and strong methodological attitude and interests. We are looking for an open-minded, curious, flexible, accurate, highly team-oriented person, capable of working independently, of quickly adjusting to changes of plan and handling workload peaks, with outstanding social and communicative skills.
The postdoctoral researcher is expected to:
participate in regular and frequent team meetings;
write code, document it properly, and cooperate with others to help get the code packaged in apt GUIs;
present intermediate research results at international workshops and conferences;
deliver a number of publications for both philosophical and computational audiences in cooperation with the PI and the other team members;
help with organizational tasks connected to the project, such as the organization of conferences and workshops (the list is non-exhaustive);
(help) disseminating results to non-specialists.


University of Amsterdam


A PhD in computational linguistics or similar field relevant to the project with demonstrable expertise in Computational Semantics;
an excellent record of international publications in venues widely recognized in the field to be of high quality;
knowledge of Python;
expertise in data-driven computational models of language, in particular distributional semantics, and ideally also knowledge-based ones, in particular ontology extraction;
excellent, preferably near-native, English;
outstanding social, organisational & communicative skills;
being able and willing to work in a team and in an interdisciplinary setting;
previous experience with similar tasks in similar research group environments in text-based humanities, an application-oriented and user-oriented attitude, and knowledge of German and other languages (especially Polish or another Slavonic language), are all advantages.

Educational level:

Ph. D.

How to apply:

Please mention NLP People as a source when applying


Tagged as: , , ,

About University of Amsterdam

Met meer dan 5000 werknemers, 30.000 studenten en een budget van ruim 600 miljoen euro, is de Universiteit van Amsterdam (UvA) een intellectueel knooppunt binnen Nederland. De UvA heeft zeven faculteiten waar onderwijs en onderzoek plaatsvinden op het gebied van geesteswetenschappen, sociale wetenschappen, economie en bedrijfskunde, rechtsgeleerdheid, natuurwetenschappen, geneeskunde en tandheelkunde. Midden in Amsterdam, op locaties waar disciplines samenkomen en elkaar beïnvloeden.

De studenten en medewerkers van de UvA zijn onafhankelijke denkers en competente rebellen. Zij durven het aan om dogma’s in twijfel te trekken en nemen geen genoegen met simpele antwoorden of standaardoplossingen. Werken bij de UvA betekent werken in een onafhankelijk, creatief, innovatief en internationaal klimaat. Kenmerkend is de open sfeer en een authentieke betrokkenheid met de stad Amsterdam en de samenleving.


With over 5,000 employe