Difference between revisions of "Continuous Bag-of-Words (CBoW)"
(Created page with "{{#seo: |title=PRIMO.ai |titlemode=append |keywords=artificial, intelligence, machine, learning, models, algorithms, data, singularity, moonshot, Tensorflow, Google, Nvidia, M...") |
|||
| Line 10: | Line 10: | ||
* [[Bag-of-Words (BOW)]] | * [[Bag-of-Words (BOW)]] | ||
* [[Natural Language Processing (NLP)]] | * [[Natural Language Processing (NLP)]] | ||
| + | * [[Word2Vec]] | ||
| + | * [[Skip-Gram]] | ||
| + | |||
* [[Scikit-learn]] Machine Learning in Python, Simple and efficient tools for data mining and data analysis; Built on NumPy, SciPy, and matplotlib | * [[Scikit-learn]] Machine Learning in Python, Simple and efficient tools for data mining and data analysis; Built on NumPy, SciPy, and matplotlib | ||
* [[Term Frequency, Inverse Document Frequency (TF-IDF)]] | * [[Term Frequency, Inverse Document Frequency (TF-IDF)]] | ||
| − | |||
* [[Doc2Vec]] | * [[Doc2Vec]] | ||
| − | + | ||
* [[Global Vectors for Word Representation (GloVe)]] | * [[Global Vectors for Word Representation (GloVe)]] | ||
* [[Feature Exploration/Learning]] | * [[Feature Exploration/Learning]] | ||
| − | + | The CBOW model architecture tries to predict the current target word (the center word) based on the source context words (surrounding words). Considering a simple sentence, “the quick brown fox jumps over the lazy dog”, this can be pairs of (context_window, target_word) where if we consider a context window of size 2, we have examples like ([quick, fox], brown), ([the, brown], quick), ([the, dog], lazy) and so on. Thus the model tries to predict the target_word based on the context_window words. [http://towardsdatascience.com/understanding-feature-engineering-part-4-deep-learning-methods-for-text-data-96c44370bbfa A hands-on intuitive approach to Deep Learning Methods for Text Data — Word2Vec, GloVe and FastText | Dipanjan Sarkar - Towards Data Science] | |
| − | |||
| − | <youtube> | + | <youtube>uskth3b6H_A</youtube> |
| − | <youtube> | + | <youtube>yBmtXtVya9A</youtube> |
| − | <youtube> | + | <youtube>UqRCEmrv1gQ</youtube> |
| − | <youtube> | + | <youtube>cNnqdz_L-eE</youtube> |
Revision as of 14:13, 12 July 2019
YouTube search... ...Google search
- Scikit-learn Machine Learning in Python, Simple and efficient tools for data mining and data analysis; Built on NumPy, SciPy, and matplotlib
- Term Frequency, Inverse Document Frequency (TF-IDF)
- Doc2Vec
The CBOW model architecture tries to predict the current target word (the center word) based on the source context words (surrounding words). Considering a simple sentence, “the quick brown fox jumps over the lazy dog”, this can be pairs of (context_window, target_word) where if we consider a context window of size 2, we have examples like ([quick, fox], brown), ([the, brown], quick), ([the, dog], lazy) and so on. Thus the model tries to predict the target_word based on the context_window words. A hands-on intuitive approach to Deep Learning Methods for Text Data — Word2Vec, GloVe and FastText | Dipanjan Sarkar - Towards Data Science
