# Empowering entity synonym set generation using flexible perceptual field and multi-layer contextual information

## TL;DR

This paper introduces a new method for generating entity synonyms using neural networks and multi-layer context, improving accuracy over previous approaches.

## Contribution

A novel approach using flexible perceptual fields and multi-layer contextual information for synonym set generation.

## Key findings

- The proposed method outperforms existing approaches on three public datasets.
- A three-layer interactive network improves synonym feature extraction by connecting entity, set, and sentence layers.
- Dynamic-weight-based synthesis enhances the accuracy of generated synonym sets.

## Abstract

Automatic generation of entity synonyms plays a pivotal role in various natural language processing applications, such as search engines, question-answering systems, and taxonomy construction. Previous research on generating entity synonym sets has typically relied on approaches that involve sorting and pruning candidate entities or solving the problem in a two-stage manner (i.e., initially identifying pairs of synonyms and subsequently aggregating them into sets). Nevertheless, these approaches tend to disregard global entity information and are susceptible to error propagation issues. This paper introduces an innovative approach to generating entity synonym sets that leverages a flexible perception mechanism and multi-layer contextual information. Firstly, to determine whether to incorporate new candidate entities into synonym sets, the approach integrates a neural network classifier with a flexible perceptual field. Within the classifier, the approach builds a three-layer interactive network, and connects the entity layer, set layer, and sentence layer to the same embedding space to extract synonym features. Secondly, we introduce a dynamic-weight-based algorithm for synthesizing entity synonym sets, leveraging a neural network classifier trained to generate entity synonym sets from the candidate entity vocabulary. Finally, extensive experimental results on three public datasets demonstrate that our approach outperforms other comparable approaches in generating entity synonym sets.