In contrast, abstraction-based methods paraphrase sections of the source document.Īll extraction-based summarizers perform the following three relatively independent tasks (Nenkova and McKeown, 2011, 2012): (a) capturing key aspects of text and storing as an intermediate representation, (b) scoring sentences in the text based on that representation, (c) and composing a summary by selecting several sentences. The critical tasks in extraction-based summarization are identifying key phrases in the document and using them to select sentences in the document for inclusion in the summary. In general, topic identification, interpretation, summary generation, and evaluation of the generated summary are the key challenges in text summarization. Most text summarization systems are based on some form of extractive summarization. Such a summary might contain words that are not explicitly present in the original document. In contrast, abstractive methods first build an internal semantic representation and then use natural language generation techniques to create a summary.
Extractive methods select a subset of existing words, phrases, or sentences in the original text to form a summary.
The two broad categories of approaches to text summarization are extraction and abstraction. Text summarization is an important NLP task, which has several applications. Gudivada, in Handbook of Statistics, 2018 12 Text Summarization
0 kommentar(er)
