- 期刊
Decorated Phrase Model and Syntax-Based Reordering Model for Statistical Machine Translation
並列摘要
In the past few years, much attention has been paid on extending phrase-based statistical machine translation with syntactic structures. In this paper, we introduce a novel phrase model, in which treebank tags are employed to decorate the bilingual phrase pairs. We use tag sequences, instead of phrase pairs, to train the lexicalized reordering model. Since the number of treebank tags is much smaller than the number of words, the tag sequence based reordering model is smaller and more accurate than the phrase based reordering model. Experiments were carried out on three types of models: the phrase model, the POS tag encapsulated phrase (PTEP) model and the syntactic tag encapsulated phrase (STEP) model. The STEP model obtained higher BLEU-4 score than other models on NIST MT tasks.
延伸閱讀
- 邱中人、沈民新（2011）。Personalized Reading Recommendation System Based on Dynamic Language Models。電腦與通訊，(139)，88-95。https://doi.org/10.29917/CCLTJ.201106.0016
- Heidel, A. (2007). Robust Unsupervised Topic-Based Language Model Adaptation [master's thesis, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU.2007.02684
- Wong, P. K. (1998). Statistical language models for Chinese recognition [doctoral dissertation, The University of Hong Kong]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0029-1812201200007604
- Ma, W. Y., & McKeown, K. (2012). Detecting and Correcting Syntactic Errors in Machine Translation Using Feature-Based Lexicalized Tree Adjoining Grammars. 中文計算語言學期刊, 17(4), 1-14. https://doi.org/10.30019/IJCLCLP.201212.0001
- 徐儀馨（2017）。Bidirectional Alignment-Collocation Models for Statistical Machine Translation〔碩士論文，國立暨南國際大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0020-1409201713191100