Exploring Content Selection in Summarization of Novel Chapters
By Faisal Ladhak, Bryan Li, Yaser Al-Onaizan, K. McKeown. 2020
39 citations recorded by the source corpus.
We present a new summarization task, generating summaries of novel chapters using summary/chapter pairs from online study guides. This is a harder task than the news summarization task, given the chapter length as well as the extreme paraphrasing and generalization found in the summaries. We focus on extractive summarization, which requires the creation of a gold-standard set of extractive summaries. We present a new metric for aligning reference summary sentences with chapter sentences to create gold extracts and also experiment with different alignment methods. Our experiments demonstrate significant improvement over prior alignment approaches for our task as shown through automatic metrics and a crowd-sourced pyramid analysis.
Subfields: Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Natural Language Processing
- Samuel R. Bowman
- Mohit Bansal
- Caiming Xiong
- Yejin Choi
- Jianfeng Gao
- Richard Socher
- Graham Neubig
- Luke S. Zettlemoyer
Citations in the corpus
- Recursively Summarizing Books with Human Feedback (2021, methodology): “Abstractive book summarization is a difficult task, where dataset collection is challenging (Mihalcea and Ceylan, 2007; Ladhak et al., 2020; Kry´sci´nski et al., 2021) and existing methods are typically either extractive (Radev et al., 2004; Mihalcea and Tarau, 2004; Bamman and Smith, 2013; Ladhak…”
- SQuALITY: Building a Long-Document Summarization Dataset the Hard Way (2022, background): “Similarly, Ladhak et al. (2020) propose a dataset for summarizing chapters of public domain books.”
- SummScreen: A Dataset for Abstractive Screenplay Summarization (2021, background): “…arXiv; Cohan et al., 2018), multiple news articles (Multi-News; Fabbri et al., 2019), opinionated text (RottenTomatoes; Wang and Ling, 2016), patents (Sharma et al., 2019), TV show stories (TVRecap; Chen and Gimpel, 2021) and (extractive summarization of) chapters of novels (Ladhak et al., 2020).”
- BookSum: A Collection of Datasets for Long-form Narrative Summarization (2021, methodology): “(Ladhak et al., 2020) computes an average of (unmodified) ROUGE-{ 1,2,L } scores between the sentence and paragraphs.”