Retrieving Multi-Entity Associations: An Evaluation of Combination Modes for Word Embeddings
This work addresses the retrieval of multi-entity associations in news events, which is an incremental improvement over existing pairwise methods.
The paper tackled the problem of retrieving multi-entity associations using word embeddings, evaluating combination modes for predicting entity participation in news events, and found that the best embedding methods did not outperform a traditional co-occurrence network baseline, especially for rare entities.
Word embeddings have gained significant attention as learnable representations of semantic relations between words, and have been shown to improve upon the results of traditional word representations. However, little effort has been devoted to using embeddings for the retrieval of entity associations beyond pairwise relations. In this paper, we use popular embedding methods to train vector representations of an entity-annotated news corpus, and evaluate their performance for the task of predicting entity participation in news events versus a traditional word cooccurrence network as a baseline. To support queries for events with multiple participating entities, we test a number of combination modes for the embedding vectors. While we find that even the best combination modes for word embeddings do not quite reach the performance of the full cooccurrence network, especially for rare entities, we observe that different embedding methods model different types of relations, thereby indicating the potential for ensemble methods.