MearcAll papers

arXiv 1301.3781 · cs.CL

Efficient Estimation of Word Representations in Vector Space

Tomas Mikolov, Kai Chen, Greg Corrado, Jeffrey Dean

Claims were extracted automatically by reducer-1 on 2026-11-12. The paper's license does not allow republishing it, so long claims are shortened to a quotation. Read the full text on arXiv.

No reproduction recordedclm_b3fb7756
We propose two novel model architectures for computing continuous vector representations of words from very large data sets.

Abstract · page 1 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_14e1044b
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 … (excerpt)

Abstract · page 1 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedclm_b24250ac
Furthermore, we show that these vectors provide state-of-the-art performance on our test set for measuring syntactic and semantic word similarities.

Abstract · page 1 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedclm_196bc13e
This choice has several good reasons - simplicity, robustness and the observation that simple models trained on huge amounts of data outperform complex systems trained on less data.

Introduction · page 1 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedclm_93c2a1c6
With progress of machine learning techniques in recent years, it has become possible to train more complex models on much larger data set, and they typically outperform the simple models.

Introduction · page 1 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_c616869d
Training a model on twice as much data using one epoch gives comparable or better results than iterating over the same data for three epochs, as is shown in Table … (excerpt)

Comparison of Model Architectures · page 8 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_1775472b
While the Skip-gram model itself does not perform on this task better than LSA similarity, the scores from this model are complementary to scores obtained with RNNLMs, and a weighted … (excerpt)

Microsoft Research Sentence Completion Challenge · page 9 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedres_225c0126
By using ten examples instead of one to form the relationship vector (we average the individual vectors together), we have observed improvement of accuracy of our best models by about … (excerpt)

Examples of the Learned Relationships · page 10 · Automated extraction, not reviewed · 0 reviewed reproductions

No reproduction recordedclm_46376b68
We believe that our comprehensive test set will help the research community to improve the existing techniques for estimating the word vectors.

Conclusion · page 10 · Automated extraction, not reviewed · 0 reviewed reproductions

Reproduced one of these claims?

Record your result in the Mearc app on your own machine, then use Publish this result with this paper's id (1301.3781) and the claim id shown next to the claim. Mearc creates a file that holds only what you choose to publish. Add it to the public claim data by pull request; a maintainer other than you reviews it before it counts.