Keyword is selected from an input document by statistical or neural techniques. Then the selected keyword is used in the decoder section for aiding the generation process. In another way contextualized key words are added in the encoding phase along with the input sequence.

San Jose State University

Keywords often represent compact representations of contents of a document. Keyword acquisition can be done in two ways
- keyword assignment
- keyword extraction

Keyword assignment means that keywords are chosen from a controlled vocabulary of terms or predefined taxonomy.

Keyword extraction selects the most representative words explicitly presented in the document, which is independent from any vocabulary.

Keyword enhanced NLG are categorized into

- Incorporate keyword assignment into text generation
- Incorporate keyword extraction into text generation


NLG Enhanced by Keywords(

A Survey of Knowledge-Enhanced Text Generation

NLG applications that are enhanced by keywords are 
 - Dialogue system
 - Summarization
 - Question generation


NLG Applications Enhanced by Keyword

A classifier helps to assign a keyword from the predetermined vocabulary to an input document.Keyword can be assigned to a document in two ways

- Adding assigned keyword into the decoder
- Assigning keyword for generated sequence


Learn Before

Related