One-to-X analogical reasoning on word embeddings: a case for diachronic armed conflict prediction from news texts
This work addresses the challenge of diachronic armed conflict prediction from news texts, offering an incremental improvement in analogical reasoning for domain-specific applications.
The paper tackles the problem of predicting new armed conflict relations (e.g., location:armed-group) from historical data by extending word analogy tasks to a one-to-X formulation, including cases with no correct answers, and demonstrates a simple threshold-based technique that reduces false positives on two corpora.
We extend the well-known word analogy task to a one-to-X formulation, including one-to-none 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 ready-to-use test set for one-to-X analogy evaluation on historical armed conflicts data.