Referring Expression Generation Using Entity Profiles

TL;DR

This paper introduces ProfileREG, a neural network model for referring expression generation that leverages entity profiles to improve generalization to unseen entities, outperforming existing methods.

Contribution

The study proposes a profile-based neural model and new evaluation setups to enhance REG's ability to handle unseen entities, addressing a key limitation of prior systems.

Findings

ProfileREG outperforms baselines in automatic evaluations

ProfileREG performs well in human evaluations

The model effectively generalizes to unseen entities

Abstract

Referring Expression Generation (REG) is the task of generating contextually appropriate references to entities. A limitation of existing REG systems is that they rely on entity-specific supervised training, which means that they cannot handle entities not seen during training. In this study, we address this in two ways. First, we propose task setups in which we specifically test a REG system's ability to generalize to entities not seen during training. Second, we propose a profile-based deep neural network model, ProfileREG, which encodes both the local context and an external profile of the entity to generate reference realizations. Our model generates tokens by learning to choose between generating pronouns, generating from a fixed vocabulary, or copying a word from the profile. We evaluate our model on three different splits of the WebNLG dataset, and show that it outperforms competitive baselines in all settings according to automatic and human evaluations.