Distributed Representations of Words and Phrases and their Compositionality
This work addresses the limitation of word representations in handling word order and idiomatic phrases, benefiting natural language processing tasks by enabling more accurate semantic modeling.
The paper tackles the problem of learning high-quality distributed vector representations for words and phrases, presenting extensions to the Skip-gram model that improve vector quality and training speed, such as subsampling frequent words and negative sampling, and enabling phrase representation learning.
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.