搜索结果: 1-12 共查到“翻译学 Machine translation”相关记录12条 . 查询时间(0.125 秒)
Phrase Dependency Machine Translation with Quasi-Synchronous Tree-to-Tree Features
phrase translation
2015/9/14
Recent research has shown clear improvement in translation quality by exploiting linguistic
syntax for either the source or target language. However, when using syntax for both languages
(“tree-to-t...
Applying Automatically Generated Semantic Knowledge A Case Study in Machine Translation
Applying Automatically Generated Semantic Knowledge Machine Translation
2015/9/2
In this paper, we discuss how we apply automatically generated semantic knowledge to benefit statisticalmachine translation (SMT). Currently, almost all statistical machine translation systems rely he...
NIST Open Machine Translation 2008 Evaluation: Stanford University’s System Description
NIST Open Machine Translation 2008 Evaluation Stanford University’s System Description
2015/6/12
This document describes Stanford University’s first entry into a NIST MT evaluation. Our entry to the 2008 evaluation mainly focused on establishing a competent baseline with a phrase-based system sim...
Optimizing Chinese Word Segmentation for Machine Translation Performance
Optimizing Chinese Word Segmentation Machine Translation Performance
2015/6/12
Previous work has shown that Chinese word segmentation is useful for machine translation to English, yet the way different segmentation strategies affect MT is still poorly understood. In this paper, ...
Disambiguating “DE” for Chinese-English Machine Translation
DE Chinese-English Machine Translation
2015/6/12
Linking constructions involving { (DE) are ubiquitous in Chinese, and can be translated into English in many different ways. This is a major source of machine translation error, even when syntaxsensit...
Textual Entailment Features for Machine Translation Evaluation
Textual Entailment Features Machine Translation Evaluation
2015/6/12
We present two regression models for the prediction of pairwise preference judgments among MT hypotheses. Both models are based on feature sets that are motivated by textual entailment and incorporate...
Robust Machine Translation Evaluation with Entailment Features
Machine Translation Evaluation Entailment Features
2015/6/12
Existing evaluation metrics for machine translation lack crucial robustness: their correlations with human quality judgments vary considerably across languages and genres. We believe that the main rea...
Stanford University’s Arabic-to-English Statistical Machine Translation System for the 2009 NIST MT Open Evaluation
Stanford University Arabic-to-English Statistical Machine Translation System the 2009 NIST MT Open
2015/6/12
This document describes Stanford University’s first entry into a NIST Arabic-English MT evaluation. We describe two main improvements over a previous Chinese-English submission (Galley et al., 2008): ...
Phrasal: A Toolkit for Statistical Machine Translation with Facilities for Extraction and Incorporation of Arbitrary Model Features
Statistical Machine Translation Extraction and Incorporation Arbitrary Model Features
2015/6/12
We present a new Java-based open source toolkit for phrase-based machine translation. The key innovation provided by the toolkit is to use APIs for integrating new features (/knowledge sources) into t...
Towards a Literary Machine Translation:The Role of Referential Cohesion
Literary Machine Translation Referential Cohesion
2015/6/10
What is the role of textual features above the sentence level in advancing the machine translation of literature? This paper examines how referential cohesion is expressed in literary and non-literary...
A News-oriented Chinese-English Machine Translation System
Multi-Engine Machine Translation Chinese Information Processing
2015/2/2
This paper introduces a News-oriented Chinese-English Machine Translation system. Firstly, general information of the system is given.Secondly, the architecture of the system –– the micro-engine pipel...
Quality and Machine Translation：A realistic objective?
Machine translation machine translation evaluation translation quality controlled language
2009/9/2
Is Machine Translation (MT) output necessarily of lower quality than human translation? Taking a user guide in English as the source text, German as the target language, and IBM WebSphere as the MT sy...