首页> 外文期刊>ACM transactions on Asian language information processing >Predictor-Estimator: Neural Quality Estimation Based on Target Word Prediction for Machine Translation
【24h】

Predictor-Estimator: Neural Quality Estimation Based on Target Word Prediction for Machine Translation

机译:Predictor-Estimator:基于目标词预测的机器翻译神经质量估计

获取原文
获取原文并翻译 | 示例
       

摘要

Recently, quality estimation has been attracting increasing interest from machine translation researchers, aiming at finding a good estimator for the "quality" of machine translation output. The common approach for quality estimation is to treat the problem as a supervised regression/classification task using a quality-annotated noisy parallel corpus, called quality estimation data, as training data. However, the available size of quality estimation data remains small, due to the too-expensive cost of creating such data. In addition, most conventional quality estimation approaches rely on manually designed features to model nonlinear relationships between feature vectors and corresponding quality labels. To overcome these problems, this article proposes a novel neural network architecture for quality estimation task-called the predictor-estimator- that considers word prediction as an additional pre-task. The major component of the proposed neural architecture is a word prediction model based on a modified neural machine translation model-a probabilistic model for predicting a target word conditioned on all the other source and target contexts. The underlying assumption is that the word prediction model is highly related to quality estimation models and is therefore able to transfer useful knowledge to quality estimation tasks. Our proposed quality estimation method sequentially trains the following two types of neural models: (1) Predictor: a neural word prediction model trained from parallel corpora and (2) Estimator: a neural quality estimation model trained from quality estimation data. To transfer word a prediction task to a quality estimation task, we generate quality estimation feature vectors from the word prediction model and feed them into the quality estimation model. The experimental results on WMT15 and 16 quality estimation datasets show that our proposed method has great potential in the various sub-challenges.
机译:近来,质量估计已引起机器翻译研究人员的越来越多的兴趣,目的是找到一种对机器翻译输出的“质量”的良好估计。质量评估的常用方法是使用质量注释的有噪并行语料库(称为质量评估数据)作为训练数据,将问题视为监督的回归/分类任务。但是,由于创建此类数据的成本太高,质量估算数据的可用大小仍然很小。另外,大多数常规的质量估计方法依赖于手动设计的特征来对特征向量和相应质量标签之间的非线性关系进行建模。为了克服这些问题,本文提出了一种用于质量估计任务的新型神经网络架构,称为“预测器估计器”,该构架将单词预测作为附加的预任务。所提出的神经体系结构的主要组成部分是基于改进的神经机器翻译模型的单词预测模型-一种概率模型,用于预测以所有其他源和目标上下文为条件的目标单词。基本假设是单词预测模型与质量估计模型高度相关,因此能够将有用的知识转移到质量估计任务中。我们提出的质量估计方法依次训练了以下两种类型的神经模型:(1)预测器:从并行语料库训练的神经词预测模型;(2)估计器:从质量估计数据训练的神经质量估计模型。为了将单词的预测任务转换为质量估计任务,我们从单词预测模型生成质量估计特征向量,并将其输入到质量估计模型中。在WMT15和16个质量估计数据集上的实验结果表明,我们提出的方法在各种子挑战中都具有巨大的潜力。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号