A Simple Theoretical Model of Importance for Summarization
Research on summarization has mainly been driven by empirical approaches, crafting systems to perform well on standard datasets with the notion of information Importance remaining latent. We argue that establishing theoretical models of Importance will advance our understanding of the task and help to further improve summarization systems. To this end, we propose simple but rigorous definitions of several concepts that were previously used only intuitively in summarization: Redundancy, Relevance, and Informativeness. Importance arises as a single quantity naturally unifying these concepts. Additionally, we provide intuitions to interpret the proposed quantities and experiments to demonstrate the potential of the framework to inform and guide subsequent works.
Code (0)
등록된 구현이 없습니다.
Tasks
InformativenessmodelSimilar Papers 제목 키워드 기반
Document Summarization with Conformal Importance Guarantees
Automatic summarization systems have advanced rapidly with large language models (LLMs), yet they still lack reliable guarantees on inclusion of critical content in high-stakes domains like healthcare, law, and finance. …
Document SummarizationScalability vs. Utility: Do We Have to Sacrifice One for the Other in Data Importance Quantification?
Quantifying the importance of each training point to a learning task is a fundamental problem in machine learning and the estimated importance scores have been leveraged to guide a range of data workflows such as data su…
Data SummarizationDomain AdaptationRead Top News First: A Document Reordering Approach for Multi-Document News Summarization
A common method for extractive multi-document news summarization is to re-formulate it as a single-document summarization problem by concatenating all documents as a single meta-document. However, this method neglects th…
Document SummarizationNews SummarizationDeep Submodular Networks for Extractive Data Summarization
Deep Models are increasingly becoming prevalent in summarization problems (e.g. document, video and images) due to their ability to learn complex feature interactions and representations. However, they do not model chara…
Data SummarizationDiversityPredicting Important Objects for Egocentric Video Summarization
We present a video summarization approach for egocentric or "wearable" camera data. Given hours of video, the proposed method produces a compact storyboard summary of the camera wearer's day. In contrast to traditional k…
Event DetectionVideo Summarization