搜索结果: 31-45 共查到“工学 translation”相关记录45条 . 查询时间(0.109 秒)
Dependency-Based Bracketing Transduction Grammar for Statistical Machine Translation
Dependency-Based Bracketing Transduction Grammar Statistical Machine Translation
font style='font-size:12px;'>
2013/4/22
In this paper, we propose a nove dependency-based bracketing transduc-tion grammar for statistical machine translation, which converts a source sen-tence into a target dependency tree. Dif-ferent from...
An Efficient Shift-Reduce Decoding Algorithm for Phrased-Based Machine Translation
Efficient Shift-Reduce Decoding Algorithm Phrased-Based Machine Translation
font style='font-size:12px;'>
2013/4/22
In statistical machine translation, decod-ing without any reordering constraint is an NP-hard problem. Inversion Transduc-tion Grammars (ITGs) exploit linguistic structure and can well balance the nee...
Machine Translation with Lattices and Forests
Machine Translation Lattices Forests
font style='font-size:12px;'>
2013/4/22
Traditional 1-best translation pipelines suffer a major drawback: the errors of 1-best outputs, inevitably introduced by each module, will propagate and accumulate along the pipeline. In order to alle...
Non-Projective Parsing for Statistical Machine Translation
Non-Projective Parsing Statistical Machine Translation
font style='font-size:12px;'>
2013/4/22
We describe a novel approach for syntaxbased statistical MT, which builds on a variant of tree adjoining grammar (TAG). Inspired by work in discriminative dependency parsing, the key idea in our appro...
A Syntax-Driven Bracketing Model for Phrase-Based Translation
A Syntax-Driven Bracketing Model Phrase-Based Translation
font style='font-size:12px;'>
2013/4/22
in the formally syntaxbased MT, a hierarchical tree generated by synchronous CFG rules associates the source sentence with the target sentence. In this paper, we propose a source dependency model to e...
11001 New Features for Statistical Machine Translation
11001 New Features Statistical Machine Translation
font style='font-size:12px;'>
2013/4/22
We use the Margin Infused Relaxed Algorithm of Crammer et al. to add a large number of new features to two machine translation systems: the Hiero hierarchical phrasebased translation system and our sy...
Fast Translation Rule Matching for Syntax-based Statistical Machine Translation
Fast Translation Rule Matching Syntax-based Statistical Machine Translation
font style='font-size:12px;'>
2013/4/22
Fast Translation Rule Matching for Syntax-based Statistical Machine Translation。
Introduction to China’s CWMT2008 Machine Translation Evaluation
Introduction China’s CWMT2008 Machine Translation Evaluation
font style='font-size:12px;'>
2013/4/22
This paper presents an overall introduction to the CWMT2008 evaluation and focuses on its two new metrics: BLEU-SBP (Chiang et al., 2008) and linguistic check-point me-thod (Zhou et al., 2008). BLEU-S...
Sub-Sentence Division for Tree-Based Machine Translation
Sub-Sentence Division Tree-Based Machine Translation
font style='font-size:12px;'>
2013/4/22
Tree-based statistical machine translation models have made significant progress in re-cent years, especially when replacing 1-best trees with packed forests. However, as the parsing accuracy usuall...
Joint Decoding with Multiple Translation Models
Joint Decoding Multiple Translation Models
font style='font-size:12px;'>
2013/4/22
Current SMT systems usually decode with single translation models and cannot ben-efit from the strengths of other models in decoding phase. We instead proposejoint decoding, a method that combines mul...
Improving Tree-to-Tree Translation with Packed Forests
Improving Tree-to-Tree Translation Packed Forests
font style='font-size:12px;'>
2013/4/22
Current tree-to-tree models suffer from parsing errors as they usually use only 1-best parses for rule extraction and decod-ing. We instead propose a forest-based tree-to-tree model that uses packed f...
Weighted Alignment Matrices for Statistical Machine Translation
Weighted Alignment Matrices Statistical Machine Translation
font style='font-size:12px;'>
2013/4/22
Current statistical machine translation sys-tems usually extract rules from bilingual corpora annotated with 1-best alignments.They are prone to learn noisy rules due to alignment mistakes. We propose...
Forest-based Translation Rule Extraction
Forest-based Translation Rule Extraction
font style='font-size:12px;'>
2013/4/22
Translation rule extraction is a fundamental problem in machine translation, especially for linguistically syntax-based systems that need parse trees from either or both sides of the bi-text. The curr...
The History of Natural Language Processing and Machine Translation
machine translation information retrieval information extraction parsing thesaurus beliefs syntactic structures semantic representations logic statistics question answering summarization psychology word-sense part-of-speech-tagging sense and reference performance case grammar agents computational semantics
font style='font-size:12px;'>
2014/3/20
The article surveys fifty years of work in computational language processing and machine translation, and suggests that a great number of the important ideas were present in the earliest days and hamp...
Application of speckle decorrelation method for small translation measurements
speckle decorrelation in-plane and normal translation
font style='font-size:12px;'>
2011/4/25
This paper analyses the usage of the speckle pattern decorrelation method for determination of small static and dynamic object translations. At first the philosophy of the method is presented briefly....