Text Summarization Task

A text summarization task is a language generation task that requires the creation of a textual summary for one or more text documents.

• Context:
  • input: a Document Set.
    • optional: a Topic/Query.
  • output: a Text Summary.
  • metric: a Text Summarization Performance Metric.
  • It can range from being a Manual Text Summarization Task to being an Automated Text Summarization Task.
  • It can range from being a Heuristic Text Summarization Task to being a Data-Driven Text Summarization Task.
  • It can range from being a Single-Document Text Summarization Task to being a Multi-Document Text Summarization Task.
  • It can range from being a Topic-focused Text Summarization Task to being a Guided Text Summarization Task.
  • It can range from being an Extractive Text Summarization Task to being an Abstractive Text Summarization Task.
  • It can be solved by a Text Summarization System (that implements a text summarization algorithm).
• Example(s):
  • News: Columbia's Newsblaster Project http://newsblaster.cs.columbia.edu/.
  • a Document Summarization Benchmark, such as a DUC Task.
  • a Opinion Summarization Task.
  • a Text Summarization via Transformer Neural Network, or a Text Summarization via Pointer-Generator Network.
  • …
• Counter-Example(s):
  • Question-Answering Task.
  • Information Extraction Task.
• See: Relation Recognition, SQuASH Project.

---

---

References

2011

• (Wikipedia - Document Summarization, 2011-Jun-13) ⇒ Wikipedia contributors. (2011). “Document Summarization." Wikipedia - The Free Encyclopedia (accessed 2011-Jun-13).
  • QUOTE: Like keyphrase extraction, document summarization hopes to identify the essence of a text. The only real difference is that now we’re dealing with larger text units — whole sentences instead of words and phrases. While some work has been done in abstractive summarization (creating an abstract synopsis like that of a human), the majority of summarization systems are extractive (selecting a subset of sentences to place in a summary).

2004

• (Hu & Liu, 2004) ⇒ Minqing Hu, Bing Liu. (2004). “Mining and Summarizing Customer Reviews.” In: Proceedings of the tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2004) doi:10.1145/1014052.1014073

2002

• (Radev et al., 2002) ⇒ Dragomir Radev, Eduard Hovy, and Kathleen R. McKeown. (2002). “Introduction to the Special Issue on Summarization.” In: Computational Linguistics, 28(4). doi:10.1162/089120102762671927

2001

• (Mani, 2001) ⇒ Inderjeet Mani. (2001). “Automatic Summarization." John Benjamins Publishing Company. ISBN:9027249865
  • QUOTE: ... Informally, the goal of text summarization is to take a textual document, extract content from it and present the most important content to the user in a condensed form and in a manner sensitive to the user's or application's needs [13].

2000

• (Hahn & Mani, 2000) ⇒ Udo Hahn, and Inderjeet Mani. (2000). “The Challenges of Automatic Summarization.” In: Computer Journal, 33(11). doi:10.1109/2.881692
  • QUOTE: Summarization -- the art of abstracting key content from one or more information sources -- has become an integral part of everyday life. People keep abreast of world affairs by listening to news bites.

1982

• (DeJong, 1982) ⇒ G. F. DeJong. (1982). “An overview of the FRUMP system.” In: Strategies for Natural Language Processing, W.G.Lehnert & M.H.Ringle (Eds).
  • Domain specific
  • Skimmed and summarised news articles.
  • Template instantiation system
  • Identified which articles belonged to a particular domain.

---