Dissertation > Excellent graduate degree dissertation topics show

Research on Dependency-based Statistical Machine Translation

Author: ZhangYu
Tutor: ZhouGuoDong
School: Suzhou University
Course: Applied Computer Technology
Keywords: statistical machine translation dependency grammar translation model template selection attachment model
CLC: TP391.2
Type: Master's thesis
Year: 2011
Downloads: 13
Quote: 0
Read: Download Dissertation

Abstract


Syntax-based statistical machine translation is becoming an active research area in recent years. Compared to the traditional phrase-based one, the syntax-based model can integrate more linguistic knowledge and thus give more guidance during translation procedure.Based on a dependency-based translation model, this paper describes the design and implementation of a dependency-based statistical machine translation system. Furthermore, some important improvements on this system are proposed in this paper.First, a baseline system based on a dependency treelet-to-string translation model is built. In this model, translation pairs of source treelets and target strings with their word alignments are learned automatically from the parsed and aligned corpus. This model allows source treelets and target strings with variables so as to handle more dependency structures. In particular a chart-style decoding algorithm with two basic operations is designed to complete the translation process.Second, it focuses on template selection and attachment operation to attach uncovered nodes to treelets. For template selection, it proposes two methods. One is adding some distinguishing template features, such as variable number penalty feature and length penalty feature. Another is adding POStags into templates. Experiments show that applying the former method can improve BLEU score by 0.0081, while the later method can not improve the performance. However, after employing POStags to classify templates, it can improve the BLEU score by matching POStag-templates first. For attachment operation, it constructs a statistical-based attachment model to guide the order of target string sequence of uncovered nodes during the decoding process. First, attached instances are extracted from training corpus, and then, features are chosen to generate the model by a Maximum Entropy classifier. Experiments show that applying the attachment model can effectively control the sequence order of target string.On the NIST MT 2005 evaluation set, the great improvement is achieved by applying template selection and the attachment model simultaneously. The best result of this system by reserving unknown words can get an improvement of 0.0021 in BLEU than Moses, and achieve the BLEU score up to 0.2540 by removing unknown words, which shows the effectiveness of our methods.

Related Dissertations

  1. The Research of Decoding Algorithm for Statistical Machine Tranlation,TP391.2
  2. Advanced alignment machine translation technology and development set selection strategy study,TP391.2
  3. An Integrated Model for C-e Government Website Translation,H315.9
  4. Research on Identification Method of Chinese Phrase Based on Semantic Analysis,TP391.43
  5. Research on Reordering Problems of Hierarchical Phrase-Based Translation Model,TP391.2
  6. Research and Implementation of Hierarchical Phrase-Based Translation Model in Statistical Machine Translation,TP391.2
  7. Word Sense Disambiguation Technology Research Based on HowNet and Bayesian Model,TP391.1
  8. Study on Word Alignment Technology and Construction of Statistical Machine Translation Platform,TP391.2
  9. Based on Dependency Treebank syntactic research Noun,H314.3
  10. Study on the Effectiveness of Group Translation,H059
  11. For specific areas of research and application of statistical machine translation,TP391.2
  12. Research on Phrase-based Statistical Machine Translation,TP391.2
  13. Comparative Study on Three Preprocessing Methods in Statistical Machine Translation,H085
  14. Study on the Translation Process: A Cognitive-psychological Perspective,H059
  15. Implementation and Analysis of Hierarchical Phrase-Based Translation Model,TP391.2
  16. An Approach to Phrase Based Log-Linear Model for Statistical Machine Translation and Its Implementation,TP391.2
  17. Research on Named Entity Processing of Statistical Machine Translaton,TP391.2
  18. Research on the Algorithms of Digital Image Inpainting,TP391.41
  19. The Research of Bilingual Corpus Mining Based on Wikipedia,TP311.13
  20. Implementation and Analysis of Tree to String Alignment Template Model in Statistical Machine Translation,TP391.2

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Translator
© 2012 www.DissertationTopic.Net  Mobile