A Comparison of Neural Models for Word Ordering

2017/08/05 by Hasler, Eva, Stahlberg, Felix, Tomalin, Marcus +2
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1708.01809

Abstract

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.

Related

• Language Models as an Alternative Evaluator of Word Order Hypotheses: A Case Study in Japanese
• Modeling Order in Neural Word Embeddings at Scale
• On the Role of Pre-trained Language Models in Word Ordering: A Case Study with BART
• Continuous Space Reordering Models for Phrase-based MT
• Studying word order through iterative shuffling