融合时态特征的日英层次短语翻译模型

doi:10.3969/j.issn.1006-2475.2017.06.001

计算机与现代化

• 人工智能 • 下一篇

融合时态特征的日英层次短语翻译模型

(北京交通大学计算机与信息技术学院，北京 100044)

收稿日期:2016-10-08 出版日期:2017-06-23 发布日期:2017-06-23
作者简介:明芳(1991-)，女，四川自贡人，北京交通大学计算机与信息技术学院硕士研究生，研究方向：自然语言处理，机器翻译; 徐金安(1970-)，男，副教授，博士，研究方向：自然语言处理，机器翻译; 王楠(1992-)，女，硕士研究生，研究方向：自然语言处理，机器翻译; 陈钰枫(1981-)，女，副教授，博士，研究方向：自然语言处理，机器翻译; 张玉洁(1961-)，女，教授，博士，研究方向：自然语言处理，机器翻译。
基金资助:
国家自然科学基金资助项目(61370130, 61473294); 中央高校基本科研业务费专项资金资助项目(2015JBM033); 科学技术部国际科技合作计划项目(K11F100010)

A Japanese-English Hierarchical Phrase-based Translation Model Integrating Tense Features

(School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China)

Received:2016-10-08 Online:2017-06-23 Published:2017-06-23

摘要/Abstract

摘要： 针对基于层次短语翻译模型的统计机器翻译使用上下文信息有限，时态翻译质量不高的问题，提出一种融合时态特征的日英统计机器翻译方法。该方法通过引入翻译规则的时态分类约束信息，解码器可以根据每条规则的潜在时态分类，为相应时态的句子匹配到最合适的规则进行翻译。首先从双语训练语料中抽取时态特征构建最大熵分类模型，然后再抽取包含各类时态信息的层次短语规则的时态特征，最后将规则的时态分类结果作为一类新特征，融入基于层次短语的翻译系统中。实验结果表明，与基线系统相比，该方法在多个测试集上提高了翻译质量，在一定程度上解决了日英层次短语模型的时态翻译问题。

关键词: 层次短语翻译模型, 时态特征, 最大熵分类模型

Abstract: In view of the problem that limited contextual information is used in the hierarchical phrase-based (HPB) translation model and the quality of tense translation is not high, this paper proposes a method to integrate tense features into Japanese-English HPB translation. Our method adopts the information of tense as constraints for tense classification model construction, and integrates tense features into HPB translation model, the decoder can get the best-matching rules according to the results of potential tense classification of rules. Firstly, we extract training data from bilingual training corpus to train tense classification models by using maximum entropy. Secondly, we extract tense features from hierarchy phrase rules to classify each kind of rules which include tense information, then we take the tense classification results as a kind of new translation features, and integrate the features into hierarchy phrase-based translation model. The experimental results show that our method can achieve good performance in Japanese-English HPB translation.

Key words: hierarchical phrase-based translation model, tense features, maximum entropy classification model

中图分类号:

TP391

明芳，徐金安，王楠，陈钰枫，张玉洁. 融合时态特征的日英层次短语翻译模型[J]. 计算机与现代化, doi: 10.3969/j.issn.1006-2475.2017.06.001.

MING Fang, XU Jin-an, WANG Nan, CHEN Yu-feng, ZHANG Yu-jie. A Japanese-English Hierarchical Phrase-based Translation Model Integrating Tense Features[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2017.06.001.

参考文献

[1] Dorr B J. A parameterized approach to integrating aspect with lexical-semantics for machine translation[C]// Proceedings of the 30th Annual Meeting on Association for Computational Linguistics. 1992:257-264.

[2] Olsen M, Traum D, Van Ess-Dykema C, et al. Implicit Cues for Explicit Generation: Using Telicity as a Cue for Tense Structure in a Chinese to English MT System[DB/OL]. http://drum.lib.umd.edu/handle/1903/1134, 2001-05-10.

[3] Wang Chao, Seneff S. High-quality speech-to-speech translation for computer-aided language learning[J]. ACM Transactions on Speech and Language Processing, 2006,3(2):1-21.

[4] Murata M, Ma Qing, Uchimoto K, et al. An Example-based Approach to Japanese-to-English Translation of Tense, Aspect, and Modality[DB/OL]. https://arxiv.org/abs/cs/9912007, 1999-12-13.

[5] Murata M, Uchimoto K, Ma Qing, et al. Using a Support-vector Machine for Japanese-to-English Translation of Tense, Aspect, and Modality[DB/OL]. https://arxiv.org/abs/cs/0112003v1, 2001-12-05.

[6] Ye Yang, Li F V, Abney S. Latent features in automatic tense translation between Chinese and English[C]// Proceedings of the 5th SIGHAN Workshop on Chinese Language Processing. 2006:48-55.

[7] Liu Feifan, Liu Fei, Liu Yang. Learning from Chinese-English parallel data for Chinese tense prediction[C]// Proceedings of the 5th International Joint Conference on Natural Language Processing. 2011:1116-1124.

[8] Xue Nianwen, Zhang Yuchen. Buy one get one free: Distant annotation of Chinese tense, event type and modality[C]// Proceedings of the 9th International Conference on Language Resources and Evaluation. 2014:1412-1416.

[9] Zhang Yuchen, Xue Nianwen. Automatic inference of the tense of Chinese events using implicit linguistic information[C]// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. 2014:1902-1911.

[10] Ge Tao, Ji Heng, Chang Baobao, et al. One tense per scene: Predicting tense in Chinese conversations[C]// Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. 2015:668-673.

[11] Tajiri T, Komachi M, Matsumoto Y. Tense and aspect error correction for ESL learners using global context[C]// Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics. 2012,2:198-202.

[12] Gong Zhengxian, Zhang Min, Tan C, et al. N-gram-based tense models for statistical machine translation[C]// Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. 2012:276-285.

[13] Gong Zhengxian, Zhang Min, Tan C, et al. Classifier-based tense model for SMT[C]// Proceedings of the 24th International Conference on Computational Linguistics. 2012:411-420.

[14] 刘文照,[日]海老原博. 日本语初级语法[M]. 上海:华东理工大学出版社, 2009.

[15] Chiang D. A hierarchical phrase-based model for statistical machine translation[C]// Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics. 2005:263-270.

[16] Och F J, Ney H. Discriminative training and maximum entropy models for statistical machine translation[C]// Proceedings of the 40th Annual Meeting on Association for Computational Linguistics. 2002:295-302.

[17] Xiao Tong, Zhu Jingbo, Zhang Hao, et al. NiuTrans: An open source toolkit for phrase-based and syntax-based machine translation[C]// Proceedings of the ACL 2012 System Demonstrations. 2012:19-24.

[18] Och F J. Minimum error rate training in statistical machine translation[C]// Proceedings of the 41st Annual Meeting on Association for Computational Linguistics. 2003,1:160-167.

[19] koehn P. Statistical significance tests for machine translation evaluation[C]// Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing. 2004:388-395.

融合时态特征的日英层次短语翻译模型

A Japanese-English Hierarchical Phrase-based Translation Model Integrating Tense Features

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	付鸿林, 张太红, 杨雅婷, 艾孜麦提·艾瓦尼尔, 马博. 基于生成对抗网络的维语场景文字修改网络[J]. 计算机与现代化, 2024, 0(01): 41-46.
[2]	王秋忆, 周浩, 郑婷婷. 改进RetinaNet的电力设备目标检测方法[J]. 计算机与现代化, 2024, 0(01): 47-52.
[3]	林启钊, 彭志平, 郭棉, 崔得龙. 基于双向多步预测的炉管温度场重构方法[J]. 计算机与现代化, 2024, 0(01): 53-58.
[4]	郑立瑞, 肖晓霞, 邹北骥, 刘彬, 周展. 基于BERT的电子病历命名实体识别[J]. 计算机与现代化, 2024, 0(01): 87-91.
[5]	李颖颖, 黄文培. 基于优化八叉树的场景视锥体裁剪算法[J]. 计算机与现代化, 2024, 0(01): 103-108.
[6]	夏千涵, 何胜煌, 吴元清, 赵乐乐. 基于可学习记忆特征金字塔网络的小样本目标检测[J]. 计算机与现代化, 2023, 0(12): 7-13.
[7]	周成诚, 曾庆军, 杨康, 胡家铭, 韩春伟. 基于高效通道注意力模块的运动想象脑电识别[J]. 计算机与现代化, 2023, 0(12): 19-23.
[8]	曾伟平, 陈俊洪, Muhammad ASIM, 刘文印, 杨振国. 基于多阶段分形组合的点云补全算法[J]. 计算机与现代化, 2023, 0(12): 24-29.
[9]	白晓波, 江梦茜, 王铁山, 邵景峰, 李勃, . 聚类质心与指数递减方法改进的哈里斯鹰算法[J]. 计算机与现代化, 2023, 0(12): 30-35.
[10]	邱凯星, 冯广. 基于双重特征注意力的多标签图像分类模型[J]. 计算机与现代化, 2023, 0(12): 41-47.
[11]	杜康, 郭鲁钰, 徐啟蕾, 单宝明, 张方坤. 基于模型种群分析变量选择的红外光谱建模方法[J]. 计算机与现代化, 2023, 0(12): 48-52.
[12]	刘语珵, 贺奇, 董延华, 王晓宇. 结合时间相关度与课程搭配度的课程推荐方法[J]. 计算机与现代化, 2023, 0(12): 53-58.
[13]	张浩洋, 尹梓名, 乐珺怡, 沈达聪, 束翌俊, 杨自逸, 孔祥勇, 龚伟. 3D-SPRNet: 一种基于并行解码器和双注意力机制的胆囊癌分割模型[J]. 计算机与现代化, 2023, 0(12): 59-66.
[14]	张伯泉, 麦海鹏, 陈嘉敏, 逄锦聚. 基于高灰度值注意力机制的脑白质高信号分割[J]. 计算机与现代化, 2023, 0(12): 67-75.
[15]	张在成, 李健. 改进的神经渲染方法在建筑施工场景中的应用[J]. 计算机与现代化, 2023, 0(12): 76-81.