Summarizing Text Summarization

There are basically two approaches to this task:

Most algorithmic methods developed are of the extractive type, while most human writers summarize using abstractive approach. There are many methods in extractive approach, such as identifying given keywords, identifying sentences similar to the title, or wrangling the text at the beginning of the documents.

How do we instruct the machines to perform extractive summarization? The authors mentioned about two representations: topic and indicator. In topic representations, frequencies, tf-idf, latent semantic indexing (LSI), or topic models (such as latent Dirichlet allocation, LDA) are used. However, simply extracting these sentences out with these algorithms may not generate a readable summary. Employment of knowledge bases or considering contexts (from web search, e-mail conversation threads, scientific articles, author styles etc.) are useful.

Evaluation on the performance on text summarization is difficult. Human evaluation is unavoidable, but with manual approaches, some statistics can be calculated, such as ROUGE.

Related posts:

Nightmares have always been part of my sleep. Just as a glass of water sits bedside and my silk mask pulls tightly across my eyes. Even with the darkest of night masks, nightmares still seep in…

We are proud to work with Real Talk: WOC & Allies to identify opportunities for white folks and others with privilege to help bridge gaps and return resources to black and native people in the United…