Fine-Grained Control of Sentence Segmentation and Entity Positioning in Neural NLG - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Fine-Grained Control of Sentence Segmentation and Entity Positioning in Neural NLG

Résumé

The move from pipeline Natural Language Generation (NLG) approaches to neural end-to-end approaches led to a loss of control in sentence planning operations owing to the conflation of intermediary micro-planning stages into a single model. Such control is highly necessary when the text should be tailored to respect some constraints such as which entity to be mentioned first, the entity position, the complexity of sentences, etc. In this paper, we introduce fine-grained control of sentence planning in neural data-to-text generation models at two levels-realization of input entities in desired sentences and realization of the input entities in the desired position among individual sentences. We show that by augmenting the input with explicit position identi-fiers, the neural model can achieve a great control over the output structure while keeping the naturalness of the generated text intact. Since sentence level metrics are not entirely suitable to evaluate this task, we used a metric specific to our task that accounts for the model's ability to achieve control. The results demonstrate that the position identifiers do constraint the neural model to respect the intended output structure which can be useful in a variety of domains that require the generated text to be in a certain structure.
Fichier principal
Vignette du fichier
INLG2019_Sentence_Planning.pdf (122.08 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02372374 , version 1 (20-11-2019)

Identifiants

  • HAL Id : hal-02372374 , version 1

Citer

Kritika Mehta, Raheel Qader, Cyril Labbé, François Portet. Fine-Grained Control of Sentence Segmentation and Entity Positioning in Neural NLG. 1st Workshop on Discourse Structure in Neural NLG, Nov 2019, Tokyo, Japan. ⟨hal-02372374⟩
126 Consultations
138 Téléchargements

Partager

Gmail Facebook X LinkedIn More