Efficient Estimation of Word Representations in Vector Space
This work addresses efficient word representation learning for natural language processing, providing state-of-the-art performance on syntactic and semantic similarity tasks.
The authors tackled the problem of computing continuous vector representations of words from large datasets, proposing two novel model architectures that achieved large improvements in accuracy at much lower computational cost (less than a day for 1.6 billion words).
We propose two novel model architectures for computing continuous vector representations of words from very large data sets. The quality of these representations is measured in a word similarity task, and the results are compared to the previously best performing techniques based on different types of neural networks. We observe large improvements in accuracy at much lower computational cost, i.e. it takes less than a day to learn high quality word vectors from a 1.6 billion words data set. Furthermore, we show that these vectors provide state-of-the-art performance on our test set for measuring syntactic and semantic word similarities.