The number of word embedding models is growing every year. Most of them are based on the co-occurrence information of words and their contexts. However, it is still an open question what is the best definition of context. We provide a systematical investigation of 4 different syntactic context types and context representations for learning word embeddings. Comprehensive experiments are conducted to evaluate their effectiveness on 6 extrinsic and intrinsic tasks. We hope that this paper, along with the published code, would be helpful for choosing the best context type and representation for a given task.
|Titel||Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing|
|Udgivelsessted||Copenhagen, Denmark, September 71, 2017|
|Status||Udgivet - 2017|