Research

Thomas Proisl

Most of my work is in the areas of language technology, cooccurrence phenomena, and stylometry/Digital Humanities. Recurring key aspects of my research are:

Language technology

I have a strong interest in natural language processing (NLP). So far, I have been active in the following areas: tokenization, part-of-speech tagging, unsupervised dependency parsing, sentiment analysis, and semantic similarity. I am (co-)developer of two state-of-the-art tools (tokenizer and part-of-speech tagger) for German web and social media texts.

Software

Key publications

Cooccurrence phenomena

I am a member in the Interdisciplinary Centre for Research on Lexicography, Valency and Collocation and a substantial part of my research is about cooccurrence phenomena like collocations or collostructions. In my (not yet published) PhD thesis, I developed a formal model for analyzing cooccurrences of arbitrary linguistic structures, e.g. dependency graphs.

Software

Key publications

Stylometry and Digital Humanities

I am a member in the Interdisciplinary Centre for Digital Humanities and a collaborator in the BMBF eHumanities Zentrum Kallimachos. My research areas include authorship attribution and linguistic and stylistic complexity.

Software

Key publications