Coordinator of Digitization and Computational Analysis Campus Lab
I got my PhD in Language Technology from Tilburg University, where I applied machine learning to model spoken dialogue phenomena such as dialogue acts, slot filling and miscommunication. I worked as a researcher in academic R&D projects since then, with the exception of one year in industry. I have been affiliated to institutions in the Netherlands: Tilburg University and The National Museum of Natural History in Leiden; in Hungary: the Language Technology Department at the Research Institute of Linguistics of the Hungarian Academy of Sciences; and Germany: Saarland University and the University of Göttingen.
My areas of competence are text mining and knowledge representation techniques, which I have applied in different genres and domains in cooperation with psychologists, folklorists, journalists and zoologists. My research focus is on using statistical language processing as enabler technology in applied end tasks. I typically analyze text, but my PhD research included audio signal data too. I have been exploring the multi-genre complexities in social media for the goal of computing the veracity of user generated content, and also had some exposure to information retrieval while employed at a web search company.
As Coordinator of the Digitization and Computational Analysis Campus Lab at Göttingen, I am strongly motivated to support Humanities and Social Sciences research via tools and approaches from language technology, driven by insights developed during my university studies in English and Russian Philology. I am founding member of the Special Interest Group of the Association for Computational Linguistics on Language Technologies for the Socio-Economic Sciences and Humanities and the workshop series on Language Technology for Cultural Heritage Data.
At the Digitization and Computational Analysis Campus Lab our target is to stimulate cross-fertilization between disciplines, with the goal of developing data scientific methods for processing Humanities and Social Sciences data. We are working toward structuring, analysis, simulation and prediction using language-informed machine learning and statistical analysis applied on data that are semi- or unstructured to convert them to machine readable networks and knowledge bases for the philological and social domains.
Please get in touch for more information about our targeted methods and upcoming use cases:
piroska (dot) lendvai (at) uni (dash) goettingen (dot) de