A Comparison of Neural Models for Word Ordering

Autor:	Hasler, Eva, Stahlberg, Felix, Tomalin, Marcus, de Gispert, Adri`a, Byrne, Bill
Rok vydání:	2017
Předmět:	Computer Science - Computation and Language
Druh dokumentu:	Working Paper
Popis:	We compare several language models for the word-ordering task and propose a new bag-to-sequence neural model based on attention-based sequence-to-sequence models. We evaluate the model on a large German WMT data set where it significantly outperforms existing models. We also describe a novel search strategy for LM-based word ordering and report results on the English Penn Treebank. Our best model setup outperforms prior work both in terms of speed and quality. Comment: Accepted for publication at INLG 2017
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1708.01809 Zobrazit plný text záznamu View this record from Arxiv