Extracting statements about causality from text documents is a challenging task in the absence of annotated training data. We create a search system for causal statements about user-specified concepts by combining pattern matching of causal connectives with semantic similarity ranking, using a language model fine-tuned for semantic textual similarity. Preliminary experiments on a small test set from Swedish governmental reports show promising results in comparison to two simple baselines.
This work was funded by Vinnova in the project 2019-02252: Datalab for results in the public sector. We thank Sven-Olof Junker, Martin Sparr, Fredrik Carlsson, Sebastian Reimann, and Gustav Finnve-den for valuable discussions. The computations were enabled by resources in project UPPMAX 2020/2-2 at the Uppsala Multidisciplinary Center for Advanced Computational Science.