# Corrected CBOW Performs as well as Skip-gram

arXiv: https://arxiv.org/abs/2012.15332 · HTML: https://mlsanity.com/paper/2012.15332/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Dec 2020.

## Built on by (most cited first, 1 of 1)

- [Predicting Anchored Text from Translation Memories for Machine Translation Using Deep Learning Methods](https://mlsanity.com/paper/2409.17939/) (2024)

## Abstract (arXiv)

Mikolov et al. (2013a) observed that continuous bag-of-words (CBOW) word embeddings tend to underperform Skip-gram (SG) embeddings, and this finding has been reported in subsequent works. We find that these observations are driven not by fundamental differences in their training objectives, but more likely on faulty negative sampling CBOW implementations in popular libraries such as the official implementation, word2vec.c, and Gensim. We show that after correcting a bug in the CBOW gradient update, one can learn CBOW word embeddings that are fully competitive with SG on various intrinsic and extrinsic tasks, while being many times faster to train.