{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/new-alignment-methods-for-discriminative-book","title":"New Alignment Methods for Discriminative Book Summarization","arxiv_id":"1305.1319","date":"2013-05-06","proceeding":null,"authors":["David Bamman","Noah A. Smith"],"abstract":"We consider the unsupervised alignment of the full text of a book with a\nhuman-written summary. This presents challenges not seen in other text\nalignment problems, including a disparity in length and, consequent to this, a\nviolation of the expectation that individual words and phrases should align,\nsince large passages and chapters can be distilled into a single summary\nphrase. We present two new methods, based on hidden Markov models, specifically\ntargeted to this problem, and demonstrate gains on an extractive book\nsummarization task. While there is still much room for improvement,\nunsupervised alignment holds intrinsic value in offering insight into what\nfeatures of a book are deemed worthy of summarization.","url_abs":"http://arxiv.org/abs/1305.1319v1","url_pdf":"http://arxiv.org/pdf/1305.1319v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":null,"task_name":"Book summarization"}],"methods":[],"datasets_introduced":[{"slug":"cmu-book-summary-dataset","name":"CMU Book Summary Dataset","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1305.1319","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}