Neural language models learn word representations that capture rich linguistic and conceptual information. Here we investigate the embeddings learned by neural machine translation models. We show that translation-based embeddings outperform those learned by cutting-edge monolingual models at single-language tasks requiring knowledge of conceptual similarity and/or syntactic role. The findings suggest that, while monolingual models learn information about how concepts are related, neural-translation models better capture their true ontological status.
@article{arxiv.1410.0718,
title = {Not All Neural Embeddings are Born Equal},
author = {Felix Hill and KyungHyun Cho and Sebastien Jean and Coline Devin and Yoshua Bengio},
journal= {arXiv preprint arXiv:1410.0718},
year = {2014}
}