Splitting text into individual words or tokens

Removing common words from text

Reducing words to their base form

Extracting named entities from text

Splitting text into individual words or tokens

Removing common words from text

Reducing words to their base form

 Extracting named entities from text

Representing text as a collection of words, disregarding grammar and word order

Weighing words based on their frequency in a document

Using vectors to represent words in a continuous vector space

Identifying topics within a collection of documents

Representing text as a collection of words, disregarding grammar and word order

Weighing words based on their frequency in a document

Using vectors to represent words in a continuous vector space

Identifying topics within a collection of documents

Determining if the sentiment expressed in text is positive, negative, or neutral

Identifying specific emotions expressed in text

Extracting named entities from text

Summarizing text by selecting key sentences

Using vectors to represent words in a continuous vector space

 Identifying specific emotions expressed in text

Grouping similar texts together without predefined labels

Identifying topics within a collection of documents

Abstractive Summarization

 Extractive Summarization

Clustering groups data without predefined labels, while classification assigns data to predefined categories

Classification is unsupervised, while clustering is supervised

Words that frequently appear together in a text

 Identifying synonyms

Translating text

 Identifying sentence structure