FACES: Diversity-Aware Entity Summarization Using Incremental Hierarchical Conceptual Clustering

Abstract

Semantic Web documents that encode facts about entities on the Web have been growing rapidly in size and evolving over time. Creating summaries on lengthy Semantic Web documents for quick identification of the corresponding entity has been of great contemporary interest. In this paper, we explore automatic summarization techniques that characterize and enable identification of an entity and create summaries that are human friendly. Specifically, we highlight the importance of diversified (faceted) summaries by combining three dimensions: diversity, uniqueness, and popularity. Our novel diversity-aware entity summarization approach mimics human conceptual clustering techniques to group facts and picks representative facts from each group to form concise (i.e., short) and comprehensive (i.e., improved coverage through diversity) summaries. We evaluate our approach against the state-of-the-art techniques and show that our work improves both the quality and the efficiency of entity summarization.

Multiple View Summarization Framework for Social Media

“…Extractive summarization methods that retain a subset of the sentences that best represent the original document include BertSum, SBert, HAHSum (Jia et al 2020), NeRoBERTa (Kwon et al 2021), DebateSum (Roush and Balaji 2020), MemSum (Gu et al 2021), etc. Entity summarization methods include FACES and FACES-E for single and multi-entity-based summaries (Gunaratna et al 2015(Gunaratna et al , 2016. Dutta et al (2019) performed the first systematic analysis of microblog summaries posted during disasters.…”

Entity Summarization in Fuzzy Knowledge Graph Based on Fuzzy Concept Analysis

“…For the research on entity summarization in KG, RELIN [9] employs a variant of the random surfer model to obtain the summarized triples and puts emphasis on the diversity of the results. Gunaratna et al [1] presented an entity summarization approach FACES that incorporating diversity, uniqueness, and popularity of the facts. Their approach utilizes the clustering algorithm Cobweb to select the representative facts.…”

“…The term Knowledge Graph (KG) was coined by Google in 2012 and KG has been successfully applied in many fields, such as entity summarization [1], entity alignment [2], etc. KG describes entities and their relationships by employing the Resource Description Framework (RDF)-style triples.…”

ESBM: An Entity Summarization BenchMark

“…As shown in Table 1, some benchmarks are no longer available. Others are available [7,8,22] but they are small and have limitations. Specifically, [22] has a task-specific nature, and [7,8] exclude classes and/or literals.…”

“…Others are available [7,8,22] but they are small and have limitations. Specifically, [22] has a task-specific nature, and [7,8] exclude classes and/or literals. These benchmarks could not support a comprehensive evaluation of general-purpose entity summarizers.…”