Dissertation > Excellent graduate degree dissertation topics show

Research on Structure Transition Technology for SMT

Author: CuiLingYun
Tutor: ZhaoTieJun
School: Harbin Institute of Technology
Course: Computer Science and Technology
Keywords: machine translation structure transition parameter training metastructure language model
CLC: TP391.2
Type: Master's thesis
Year: 2008
Downloads: 63
Quote: 0
Read: Download Dissertation

Abstract


In the field of machine translation, phrase-based MT approach is the most mature and stable method, but now it is difficult to improve. The phrase-based model can give a more accurate translation if the phrase has appeared in the corpus. The more accurate translation includes the choice of words and the order adjustment of the words with in the phrase. However, it is difficult to give an effective solution to dealing with the unseen phrases and the order adjustment between phrases, because this method didn’t use syntax information and complex semantics knowledge. For this reason, people hope to introduce the deeper linguistics structure to improve the performance of the existing methods. One of the most direct ideas is to introduce syntactic structure and built SMT model in this structure.This paper presents a novel structure transition model from Recombination of MS (RM) on the source side to the RM on the target side. In this model translation pair of source RM and target RM with their word alignments are learned automatically form the parsed and aligned corpus, and we compute the translation probability. To control the order adjustment we analyze the difference between linear language model and the non-linear language model, and imply a non-linear model of meta-structure.In this paper, minimum error rate training method was used to train the parameters of log-linear model. It used the same evaluation criteria BLEU with the Automatic Evaluation System. The multi-dimension optimization problem is settled in different one-dimension spaces. We give the algorithm to find the set of the discrete solution candidates for the continuous multi-dimension optimization problem. The training time needed for the model is reduced and the results valued with BLEU are improved.Finally, we combined the structure transition model with the SMT system, and use the structure transition model to hide the heterogeneous phenomenon of syntactic structure between source and target languages. And also, long-distance order adjustment became local RM order adjustment. Experiments show that the model significantly outperforms Pharaoh, a phrase-based system.

Related Dissertations

  1. Word Sense Disambiguation Corpus Automatic Acquisition,TP391.1
  2. The Research of Decoding Algorithm for Statistical Machine Tranlation,TP391.2
  3. A Comparative Study of Chinese and English Passive Construction Based on Information Dependency Language Model,H314.3
  4. Probability and statistics based on dictionaries and Chinese word segmentation algorithm,TP391.1
  5. On-Line Handwritten Chinese Character Recognition Approach Based on Sentence Level,TP391.43
  6. The Analysis of Financial Institutions Structure’s Changing Motivation,F224
  7. Study on Word Alignment Technology and Construction of Statistical Machine Translation Platform,TP391.2
  8. The Influence of Structure Transition on Solidification and Welding Properties of Sn-Based Lead-Free Solder,TG42
  9. Research on Automatic Evaluation of Machine Translation Based on Linguistic Knowledge,TP391.2
  10. Research on Information Retrieval Models Based on Reference Document,TP391.3
  11. Research on Computing Granularities of Automatic Machine Translation Evaluation,TP391.2
  12. Chinese Continuous Speech Recognition Based on Sphinx,TN912.34
  13. Deployment and configuration of component-oriented model semantics and implementation of security mechanisms,TP311.52
  14. An Approach to Phrase Based Log-Linear Model for Statistical Machine Translation and Its Implementation,TP391.2
  15. Research of Chinese Phrase Identification Based on Conditional Random Fields,TP391.1
  16. The Design and Practice of Ningxia Telecom Business Navigator System,TP311.52
  17. Design and Implementation of Automatical Recognition of Chinese Personal Name,TP391.1
  18. Sentence- aligned parallel corpus and its application in machine translation,H315.9
  19. Information Geometry Based Pure High-order Interaction Model and Its Applications,TP391.1
  20. Research on Reordering Problems of Hierarchical Phrase-Based Translation Model,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