Task-Oriented Learning of Word Embeddings for Semantic Relation Classification
Kazuma Hashimoto, Pontus Stenetorp, Makoto Miwa, Yoshimasa Tsuruoka · 2015
We present a novel learning method for word embeddings designed for relation classification.Our word embeddings are trained by predicting words between noun pairs using lexical relation-specific features on a large unlabeled corpus.This allows us to explicitly incorporate relationspecific information into the word embeddings.The learned word embeddings are then used to construct feature vectors for a relation classification model.On a wellestablished semantic relation classification task, our method significantly outperforms a baseline based on a previously introduced word embedding method, and compares favorably to previous state-of-the-art models that use syntactic information or manually constructed external resources.