Comparison between cbow, skip gram and skip-gram with subword information (1)
0 likes228 views
The document compares CBOW and Skip-gram models for word embeddings, highlighting differences in training data and model settings. It addresses tasks related to the similarity of concepts, words, and phrases, along with performance metrics like precision and recall. The text concludes that plain word embeddings fail to capture nuanced semantic relationships and depend heavily on the quality of the training data.
![Comparison Between CBOW, Skip-
Gram and Skip-Gram with Subword
Information [ See article ]
By: Kavita Ganesan
www.kavita-ganesan.com](https://image.slidesharecdn.com/comparisonbetweencbowskip-gramandskip-gramwithsubwordinformation1-200424151525/85/Comparison-between-cbow-skip-gram-and-skip-gram-with-subword-information-1-1-320.jpg)
Comparison between cbow, skip gram and skip-gram with subword information (1)
- 1. Comparison Between CBOW, Skip- Gram and Skip-Gram with Subword Information [ See article ] By: Kavita Ganesan www.kavita-ganesan.com
- 2. CBOW This is a visual comparison sum visual thisis acomparison visual thisis acomparison visual visual visual target word By: Kavita Ganesan target word SkipGram
- 3. This is a visual comparison sum visual th ishi target word SkipGram + Subword (SkipGramSI) this<t s>
- 4. Training Data & Model Settings
- 6. Differences in Training time With Gensim
- 7. Task 1: Most related concepts
- 12. Task 2: Similarity between words
- 14. Task 3: Similarity between phrases
- 15. Dataset
- 16. Precision, Recall & F-Score Cosine threshold = 0.6
- 17. Raw Predictions
- 18. Final Thoughts Plain word embeddings: ● Does not capture fine-grained semantic similarity ● Words are not directly replaceable with words closest in vector space ● Quality of embeddings is only as good as the training data