New Alignment Methods for Discriminative Book Summarization

By David Bamman, Noah A. Smith. 2013

36 citations recorded by the source corpus.

We consider the unsupervised alignment of the full text of a book with a human-written summary. This presents challenges not seen in other text alignment problems, including a disparity in length and, consequent to this, a violation of the expectation that individual words and phrases should align, since large passages and chapters can be distilled into a single summary phrase. We present two new methods, based on hidden Markov models, specifically targeted to this problem, and demonstrate gains on an extractive book summarization task. While there is still much room for improvement, unsupervised alignment holds intrinsic value in offering insight into what features of a book are deemed worthy of summarization.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

1. Noah A. Smith
2. Mohit Bansal
3. Yejin Choi
4. Luke S. Zettlemoyer
5. Percy Liang
6. Jeff Wu
7. Jan Leike
8. Sam Thomson

In Natural Language Processing

1. Mohit Bansal
2. Noah A. Smith
3. Sam Thomson
4. Fei Liu
5. Ryan J. Lowe
6. Jeff Wu
7. Norman M. Sadeh
8. Jan Leike

Citations in the corpus

• Recursively Summarizing Books with Human Feedback (2021, methodology): “For example, Bamman and Smith (2013) has 439 (book, summary) pairs.”
• Toward Abstractive Summarization Using Semantic Representations (2018, background): “Demand is on the rise for high-quality summaries not just for lengthy texts (e.g., books; Bamman and Smith, 2013) and texts known to be prohibitively difficult for people to understand (e.g., website privacy policies; Sadeh et al., 2013), but also for non-textual media (e.g., videos and image…”