Automatic Summarization
Automatic Summarization
Automatic Summarization
order to create a summary with the major points of original document. Technologies that
can make a coherent summary take into account variables such as length, writing style and
syntax.
Types:
Extraction based summarization
Abstraction based summarization
Aided summarization
Extraction based summarization:
Automatic system extracts objects from entire collection without modifying the
objects themselves
Merely copy the information deemed most important by the system to summary
Example:
o Key phrase extraction where the goal is to select individual words or phrases
to tag a document
o A document summarization where the goal is to select a whole sentences
without modifying them to create a short paragraph summary
Abstraction based summarization:
Involves paraphrasing sections of the source document
In general, abstraction can condense a text more strongly than extraction
Programs for this are harder to develop as they require the use of natural language
generation technology
Aided summarization:
Machine learning techniques from closely related fields such as Information retrieval or
Text mining have been successfully adapted to help automatic summarization. Apart from
Fully Automated Summarizers, there are systems that aid users with the task of
summarization (Machine aided human summarization).
Such as by highlighting candidate passages to be included in the summary and there are
processes that depend on post-processing by human(Human aided machine
summarization).
Application and systems for summarization:
Broadly two types of extractive summarization tasks depending on what the
summarization program focuses on
Generic summarization
Query relevant summarization/ Query based summarization
Genetic summarization focuses on obtaining generic summary or abstraction of collection,
query relevant summarization summarizes objects specific to query.