Task-Oriented Learning of Word Embeddings for Semantic Relation Classification
Abstract
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 relation-specific information into the word embeddings. The learned word embeddings are then used to construct feature vectors for a relation classification model. On a well-established 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.
Cite
@article{arxiv.1503.00095,
title = {Task-Oriented Learning of Word Embeddings for Semantic Relation Classification},
author = {Kazuma Hashimoto and Pontus Stenetorp and Makoto Miwa and Yoshimasa Tsuruoka},
journal= {arXiv preprint arXiv:1503.00095},
year = {2015}
}
Comments
The Nineteenth Conference on Computational Natural Language Learning (CoNLL 2015)