Abstractive Sentence Summarization Task

An Abstractive Sentence Summarization Task is a sentence summarization task that allows for paraphrasing.

• Context:
  • It can be solved by an Abstractive Sentence Summarization System (that implements an abstractive summarization algorithm).
• See: Extractive Sentence Summarization.

---

---

References

2015

• (Rush et al., 2015) ⇒ Alexander M. Rush, Sumit Chopra, and Jason Weston. (2015). “A Neural Attention Model for Abstractive Sentence Summarization.” In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP-2015).
  • QUOTE: … We begin by defining the sentence summarization task. Given an input sentence, the goal is to produce a condensed summary. Let the input consist of a sequence of [math]\displaystyle{ M }[/math] words [math]\displaystyle{ x_1,..., x_M }[/math] coming from a fixed vocabulary [math]\displaystyle{ V }[/math] of size [math]\displaystyle{ |V|= V }[/math]. We will represent each word as an indicator vector [math]\displaystyle{ x_i \in {0,1}^V }[/math] for [math]\displaystyle{ i \in {1,..., M} }[/math], sentences as a sequence of indicators, and [math]\displaystyle{ X }[/math] as the set of possible inputs. Furthermore define the notation [math]\displaystyle{ x_{[i,j,k]} }[/math] to indicate]] the sub-sequence of elements [math]\displaystyle{ i, j, k }[/math]. …

---