AutoSUM: Automating Feature Extraction and Multi-user Preference Simulation for Entity Summarization

TL;DR

AutoSUM introduces an automated approach for feature extraction and multi-user preference simulation in entity summarization, achieving state-of-the-art results without relying on handcrafted features or extensive human expertise.

Contribution

The paper presents AutoSUM, a novel integrated method combining BiLSTM-based feature extraction and a two-phase attention mechanism for preference simulation in entity summarization.

Findings

AutoSUM outperforms existing methods on DBpedia and LinkedMDB datasets.

It achieves higher F-measure and MAP scores.

The approach reduces reliance on manual feature engineering.

Abstract

Withthegrowthofknowledgegraphs, entity descriptions are becoming extremely lengthy. Entity summarization task, aiming to generate diverse, comprehensive, and representative summaries for entities, has received increasing interest recently. In most previous methods, features are usually extracted by the handcrafted templates. Then the feature selection and multi-user preference simulation take place, depending too much on human expertise. In this paper, a novel integration method called AutoSUM is proposed for automatic feature extraction and multi-user preference simulation to overcome the drawbacks of previous methods. There are two modules in AutoSUM: extractor and simulator. The extractor module operates automatic feature extraction based on a BiLSTM with a combined input representation including word embeddings and graph embeddings. Meanwhile, the simulator module automates multi-user preference simulation based on a well-designed two-phase attention mechanism (i.e., entity-phase attention and user-phase attention). Experimental results demonstrate that AutoSUM produces state-of-the-art performance on two widely used datasets (i.e., DBpedia and LinkedMDB) in both F-measure and MAP.