One-to-X Analogical Reasoning on Word Embeddings: a Case for Diachronic Armed Conflict Prediction from News Texts
Andrey Kutuzov, Erik Velldal, Lilja Øvrelid · 2019
We extend the well-known word analogy task to a one-to-X formulation, including one-tonone cases, when no correct answer exists.The task is cast as a relation discovery problem and applied to historical armed conflicts datasets, attempting to predict new relations of type 'location:armed-group' based on data about past events.As the source of semantic information, we use diachronic word embedding models trained on English news texts.A simple technique to improve diachronic performance in such task is demonstrated, using a threshold based on a function of cosine distance to decrease the number of false positives; this approach is shown to be beneficial on two different corpora.Finally, we publish a readyto-use test set for one-to-X analogy evaluation on historical armed conflicts data.