{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,3,26]],"date-time":"2024-03-26T02:14:25Z","timestamp":1711419265849},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"16","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"Unsupervised extractive summarization is an important technique in information extraction and retrieval. Compared with supervised method, it does not require high-quality human-labelled summaries for training and thus can be easily applied for documents with different types, domains or languages. Most of existing unsupervised methods including TextRank and PACSUM rely on graph-based ranking on sentence centrality. However, this scorer can not be directly applied in end-to-end training, and the positional-related prior assumption is often needed for achieving good summaries. In addition, less attention is paid to length-controllable extractor, where users can decide to summarize texts under particular length constraint. This paper introduces an unsupervised extractive summarization model based on a siamese network, for which we develop a trainable bidirectional prediction objective between the selected summary and the original document. Different from the centrality-based ranking methods, our extractive scorer can be trained in an end-to-end manner, with no other requirement of positional assumption. In addition, we introduce a differentiable length control module by approximating 0-1 knapsack solver for end-to-end length-controllable extracting. Experiments show that our unsupervised method largely outperforms the centrality-based baseline using a same sentence encoder. In terms of length control ability, via our trainable knapsack module, the performance consistently outperforms the strong baseline without utilizing end-to-end training. Human evaluation further evidences that our method performs the best among baselines in terms of relevance and consistency.<\/jats:p>","DOI":"10.1609\/aaai.v38i16.29797","type":"journal-article","created":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T11:56:32Z","timestamp":1711367792000},"page":"18372-18380","source":"Crossref","is-referenced-by-count":0,"title":["Unsupervised Extractive Summarization with Learnable Length Control Strategies"],"prefix":"10.1609","volume":"38","author":[{"given":"Renlong","family":"Jie","sequence":"first","affiliation":[]},{"given":"Xiaojun","family":"Meng","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Qun","family":"Liu","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2024,3,24]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/29797\/31378","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/29797\/31379","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/29797\/31378","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T11:56:32Z","timestamp":1711367792000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/29797"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,24]]},"references-count":0,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2024,3,25]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v38i16.29797","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2024,3,24]]}}}