Abstract

Syntactic language models and N-gram language models have both been used in word ordering. In this paper, we give an empirical comparison between N-gram and syntactic language models on word order task. Our results show that the quality of automatically-parsed training data has a relatively small impact on syntactic models. Both of syntactic and N-gram models can benefit from large-scale raw text. Compared with N-gram models, syntactic models give overall better performance, but they require much more training time. In addition, the two models lead to different error distributions in word ordering. A combination of the two models integrates the advantages of each model, achieving the best result in a standard benchmark.

Highlights

  • N-gram language models have been used in a wide range of the generation tasks, such as machine translation (Koehn et al, 2003; Chiang, 2007; Galley et al, 2004), text summarization (Barzilay and McKeown, 2005) and realization (Guo et al, 2011)

  • Syntactic language models have been used as a complement or alternative to Ngram language models for machine translation (Charniak et al, 2003; Shen et al, 2008; Schwartz et al, 2011), syntactic analysis (Chen et al, 2012) and tree linearization (Song et al, 2014)

  • We develop a combined model by discretizing probability from N-gram model, and using them as features in the syntactic model

Read more

Summary

Introduction

N-gram language models have been used in a wide range of the generation tasks, such as machine translation (Koehn et al, 2003; Chiang, 2007; Galley et al, 2004), text summarization (Barzilay and McKeown, 2005) and realization (Guo et al, 2011) Such models are trained from large-scale raw text, capturing distributions of local word Ngrams, which can be used to improve the fluency of synthesized text. There has been two main types of syntactic language models in the literature, the first being relatively more oriented to syntactic structure, without an explicit emphasis on word orders (Shen et al, 2008; Chen et al, 2012). The combined model gives the best results in a standard benchmark

Syntactic word ordering
N-gram word ordering
Experimental settings
Evaluation metrics
Data preparation
In-domain word ordering
Cross-domain word ordering
Influence of data scale
Influence on BLEU and METEOR
Influence on training time
Error analysis
Sentence length
Distortion range
Constituent span
N-gram language model feature
Final results
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call