arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1610.04841cs.CL
收藏

基于循环神经网络的翻译质量评估

Translation Quality Estimation using Recurrent Neural Network

CDAC Mumbai(孟买先进计算发展中心)

Raj Nath Patel, Sasikumar M

摘要:

本文介绍了我们在第一届统计机器翻译会议(WMT 16)上提交的关于词/短语级质量估计(QE)的共享任务。共享任务的目的是预测给定单词/短语在给定句子中是否是正确/不正确(OK/BAD)的翻译。本文提出了一种基于循环神经网络语言模型(RNN-LM)结构的词级质量估计方法。已经发现RNN-LM在不同的自然语言处理(NLP)应用中非常有效。RNN-LM主要用于不同NLP问题的向量空间语言建模。为此,我们修改了RNN-LM的架构。修改后的系统预测槽中的标签(OK/BAD),而不是预测单词。系统的输入是一个单词序列,类似于标准的RNN-LM。该方法与语言无关,只需要QE的翻译文本。为了估计短语级质量,我们使用单词级QE系统的输出。

英文摘要:

This paper describes our submission to the shared task on word/phrase level Quality Estimation (QE) in the First Conference on Statistical Machine Translation (WMT16). The objective of the shared task was to predict if the given word/phrase is a correct/incorrect (OK/BAD) translation in the given sentence. In this paper, we propose a novel approach for word level Quality Estimation using Recurrent Neural Network Language Model (RNN-LM) architecture. RNN-LMs have been found very effective in different Natural Language Processing (NLP) applications. RNN-LM is mainly used for vector space language modeling for different NLP problems. For this task, we modify the architecture of RNN-LM. The modified system predicts a label (OK/BAD) in the slot rather than predicting the word. The input to the system is a word sequence, similar to the standard RNN-LM. The approach is language independent and requires only the translated text for QE. To estimate the phrase level quality, we use the output of the word level QE system.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑