Small data, big challenges: Concept drift for multilingual philosophy corpora
In this project philosophers and computational linguists conduct an interdisciplinary pilot study with the aim of combining the strengths of both fields. Concepts such as science, marriage or evolution change through time. In philosophy, conceptual changes are studied in a few technical texts at a time by painstaking manual analysis. In computational linguistics, conceptual changes are studied in massive, generic corpora such as the whole of Wikipedia. The current challenge in philosophy is to obtain fine-grained analyses at a bigger scale (Betti & van den Berg 2016). The current challenge in computational linguistics is to detect non-trivial shifts of meaning while increasing reliability by a firm methodological grasp of the real factors influencing the results (Hellrich & Hahn 2016). We will address these challenges by studying to what extent, and under which constraints, we can soundly detect concept drift via word embeddings in small philosophy corpora.
Prof. Dr. A. Betti is Professor of Philosophy of Language at the UvA.
Dr. L. Beinborn is an academic researcher specialized in computational linguistics and natural language processing at the UvA.
Dr. A.S. Fokkens is Associate Professor at the Vrije Universiteit Amsterdam.