Accès ouvert

Recursive Top-Down Production for Sentence Generation with Latent Trees

Article scientifique 2020 Anglais

Résumé

We model the recursive production property of context-free grammars for natural and synthetic languages. To this end, we present a dynamic programming algorithm that marginalises over latent binary tree structures with N leaves, allowing us to compute the likelihood of a sequence of N tokens under a latent tree model, which we maximise to train a recursive neural function. We demonstrate performance on two synthetic tasks: SCAN (Lake and We also present experimental results on German-English translation on the Multi30k dataset

Citer ce document

Tan, S., Shen, Y., Sordoni, A., Courville, A., O’Donnell, T. (2020). Recursive Top-Down Production for Sentence Generation with Latent Trees. https://doi.org/10.18653/v1/2020.findings-emnlp.208

Accès au document

Voir sur le dépôt source

Ce document est hébergé sur son dépôt institutionnel d'origine.

Auteur(s)

Shawn Tan Yikang Shen Alessandro Sordoni Aaron Courville Timothy J. O’Donnell

Statistiques

Consultations : 1

Téléchargements : 0