Temporal dynamics of semantic relations in word embeddings: an application to predicting armed conflict participants
This work addresses a domain-specific problem for conflict prediction researchers, but it is incremental as it extends existing analogy tasks with a time dimension.
The paper tackles the problem of predicting which insurgent armed groups will be active in specific geographical locations over time by using word embeddings to trace temporal semantic relations, and it shows the method outperforms baselines on UCDP Armed Conflicts data from 1994-2010.
This paper deals with using word embedding models to trace the temporal dynamics of semantic relations between pairs of words. The set-up is similar to the well-known analogies task, but expanded with a time dimension. To this end, we apply incremental updating of the models with new training texts, including incremental vocabulary expansion, coupled with learned transformation matrices that let us map between members of the relation. The proposed approach is evaluated on the task of predicting insurgent armed groups based on geographical locations. The gold standard data for the time span 1994--2010 is extracted from the UCDP Armed Conflicts dataset. The results show that the method is feasible and outperforms the baselines, but also that important work still remains to be done.