%0 Generic %1 mikolov2013distributed %A Mikolov, Tomas %A Sutskever, Ilya %A Chen, Kai %A Corrado, Greg %A Dean, Jeffrey %D 2013 %K thema:semcomp %T Distributed Representations of Words and Phrases and their Compositionality %U http://arxiv.org/abs/1310.4546 %X The recently introduced continuous Skip-gram model is an efficient method for learning high-quality distributed vector representations that capture a large number of precise syntactic and semantic word relationships. In this paper we present several extensions that improve both the quality of the vectors and the training speed. By subsampling of the frequent words we obtain significant speedup and also learn more regular word representations. We also describe a simple alternative to the hierarchical softmax called negative sampling. An inherent limitation of word representations is their indifference to word order and their inability to represent idiomatic phrases. For example, the meanings of "Canada" and Äir" cannot be easily combined to obtain Äir Canada". Motivated by this example, we present a simple method for finding phrases in text, and show that learning good vector representations for millions of phrases is possible.

@misc{mikolov2013distributed, abstract = {The recently introduced continuous Skip-gram model is an efficient method for learning high-quality distributed vector representations that capture a large number of precise syntactic and semantic word relationships. In this paper we present several extensions that improve both the quality of the vectors and the training speed. By subsampling of the frequent words we obtain significant speedup and also learn more regular word representations. We also describe a simple alternative to the hierarchical softmax called negative sampling. An inherent limitation of word representations is their indifference to word order and their inability to represent idiomatic phrases. For example, the meanings of "Canada" and "Air" cannot be easily combined to obtain "Air Canada". Motivated by this example, we present a simple method for finding phrases in text, and show that learning good vector representations for millions of phrases is possible.}, added-at = {2018-11-22T11:11:06.000+0100}, author = {Mikolov, Tomas and Sutskever, Ilya and Chen, Kai and Corrado, Greg and Dean, Jeffrey}, biburl = {https://www.bibsonomy.org/bibtex/237fb87615c89155bc5cceb0fe4468036/benwesterath}, description = {[1310.4546] Distributed Representations of Words and Phrases and their Compositionality}, interhash = {4d7ff49f008ec05928f11e50f2db1cf9}, intrahash = {37fb87615c89155bc5cceb0fe4468036}, keywords = {thema:semcomp}, note = {cite arxiv:1310.4546}, timestamp = {2018-11-22T11:11:06.000+0100}, title = {Distributed Representations of Words and Phrases and their Compositionality}, url = {http://arxiv.org/abs/1310.4546}, year = 2013 }