Traversal-Free Word Vector Evaluation in Analogy Space
Xiaoyin Che | Nico Ring | Willi Raschkowski | Haojin Yang | Christoph Meinel
Proceedings of the 2nd Workshop on Evaluating Vector Space Representations for NLP
In this paper, we propose an alternative evaluating metric for word analogy questions (A to B is as C to D) in word vector evaluation. Different from the traditional method which predicts the fourth word by the given three, we measure the similarity directly on the “relations” of two pairs of given words, just as shifting the relation vectors into a new analogy space. Cosine and Euclidean distances are then calculated as measurements. Observation and experiments shows the proposed analogy space evaluation could offer a more comprehensive evaluating result on word vectors with word analogy questions. Meanwhile, computational complexity are remarkably reduced by avoiding traversing the vocabulary.