This content was deleted by the author. You can see it from Blockchain History logs.

Classification of Summarization system

Classification of Summarization system

1. Based on Approach

There are two strategies for summarization those are summarization by extraction, which consists of extracting source sentences as it is and adding into a summary, and summarization by abstraction, which involves generating novel sentences for the summary. The need for abstraction is especially high when opinions are diverse.

2. Based on type of Detail

There are 2 types informative or indicative. . An indicative summary is used for quick view of a lengthy document and it provides only the main idea of the original text. These are usually small and it encourages a user to read the original document. Informative summary serves as a substitution to the original document. It provides the concise information about the original document to the user.

3. Based on type of content

This classification is based on the type of content in the original document. Generic summarization is system which can be used by any type of the user and summary does not depend on the subject of the document. All the information is at same level of importance and which is not user specific. Query-based summarization is question answer type where the summary is the result of query. It provides the users view and cannot be used by any type of user.

4. Based on limitation:-

Genre specific systems only accept special type of input like newspaper articles, stories, manuals etc. Limited to the type of input they can accept.Domain independent system can accept different type of text. They are not dependent on the domain and can be used by any type of user.

5. Based on number of input documents

Summarization can be classified based on whether a system accepts one or more documents as input.

6. Based on language that are Mono-Lingual and Multi-Lingual