Query-Specific Knowledge Summarization with Entity Evolutionary Networks

TL;DR

This paper introduces SetEvolve, a framework for query-specific knowledge summarization that captures evolving connections among entities over time using graphical models, enabling insightful and structural knowledge retrieval.

Contribution

The paper proposes a novel framework, SetEvolve, for modeling and summarizing evolving entity connections in response to specific queries, advancing knowledge retrieval techniques.

Findings

SetEvolve effectively captures entity connection evolution patterns.

Experiments demonstrate the framework's utility on synthetic and real data.

Case studies show improved knowledge understanding for queries.

Abstract

Given a query, unlike traditional IR that finds relevant documents or entities, in this work, we focus on retrieving both entities and their connections for insightful knowledge summarization. For example, given a query "computer vision" on a CS literature corpus, rather than returning a list of relevant entities like "cnn", "imagenet" and "svm", we are interested in the connections among them, and furthermore, the evolution patterns of such connections along particular ordinal dimensions such as time. Particularly, we hope to provide structural knowledge relevant to the query, such as "svm" is related to "imagenet" but not "cnn". Moreover, we aim to model the changing trends of the connections, such as "cnn" becomes highly related to "imagenet" after 2010, which enables the tracking of knowledge evolutions. In this work, to facilitate such a novel insightful search system, we propose \textsc{SetEvolve}, which is a unified framework based on nonparanomal graphical models for evolutionary network construction from large text corpora. Systematic experiments on synthetic data and insightful case studies on real-world corpora demonstrate the utility of \textsc{SetEvolve}.