Exploring Explainable Selection to Control Abstractive Summarization

Haonan Wang, Yang Gao*, Yu Bai, Mirella Lapata, Heyan Huang

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

10 引用 (Scopus)

摘要

Like humans, document summarization models can interpret a document's contents in a number of ways. Unfortunately, the neural models of today are largely black boxes that provide little explanation of how or why they generated a summary in the way they did. Therefore, to begin prying open the black box and to inject a level of control into the substance of the final summary, we developed a novel select-and-generate framework that focuses on explainability. By revealing the latent centrality and interactions between sentences, along with scores for sentence novelty and relevance, users are given a window into the choices a model is making and an opportunity to guide those choices in a more desirable direction. A novel pair-wise matrix captures the sentence interactions, centrality and attribute scores, and a mask with tunable attribute thresholds allows the user to control which sentences are likely to be included in the extraction. A sentence-deployed attention mechanism in the abstractor ensures the final summary emphasizes the desired content. Additionally, the encoder is adaptable, supporting both Transformer- and BERTbased configurations. In a series of experiments assessed with ROUGE metrics and two human evaluations, ESCA outperformed eight state-of-the-art models on the CNN/DailyMail and NYT50 benchmark datasets.

源语言英语
主期刊名35th AAAI Conference on Artificial Intelligence, AAAI 2021
出版商Association for the Advancement of Artificial Intelligence
13933-13941
页数9
ISBN(电子版)9781713835974
出版状态已出版 - 2021
活动35th AAAI Conference on Artificial Intelligence, AAAI 2021 - Virtual, Online
期限: 2 2月 20219 2月 2021

出版系列

姓名35th AAAI Conference on Artificial Intelligence, AAAI 2021
15

会议

会议35th AAAI Conference on Artificial Intelligence, AAAI 2021
Virtual, Online
时期2/02/219/02/21

指纹

探究 'Exploring Explainable Selection to Control Abstractive Summarization' 的科研主题。它们共同构成独一无二的指纹。

引用此

Wang, H., Gao, Y., Bai, Y., Lapata, M., & Huang, H. (2021). Exploring Explainable Selection to Control Abstractive Summarization. 在 35th AAAI Conference on Artificial Intelligence, AAAI 2021 (页码 13933-13941). (35th AAAI Conference on Artificial Intelligence, AAAI 2021; 卷 15). Association for the Advancement of Artificial Intelligence.