Zhengxian Gong

Learn More
Statistical machine translation systems are usually trained on a large amount of bilingual sentence pairs and translate one sentence at a time, ignoring document-level information. In this paper, we propose a cache-based approach to document-level translation. Since caches mainly depend on relevant data to supervise subsequent decisions, it is critical to(More)
Tense is a small element to a sentence, however , error tense can raise odd grammars and result in misunderstanding. Recently, tense has drawn attention in many natural language processing applications. However, most of current Statistical Machine Translation (SMT) systems mainly depend on translation model and language model. They never consider and make(More)
Currently, there are many researches focusing on grid scheduling and more and more scheduling algorithms were proposed. However, those algorithms are not satisfied with the requirement of the grid for ignoring its characteristics of dynamics, autonomy, distributing, etc. Therefore, this paper proposes an adaptable dynamic job scheduling approach based on(More)
Current Statistical Machine Translation (SMT) is significantly affected by Machine Translation (MT) evaluation metric. Nowadays the emergence of document-level MT research increases the demand for corresponding evaluation metric. This paper proposes two superior yet low-cost quantitative objective methods to enhance traditional MT metric by modeling(More)
Document-level Machine Translation (MT) has been drawing more and more attention due to its potential of resolving sentence-level ambiguities and inconsistencies with the benefit of wide-range context. However, the lack of simple yet effective evaluation metrics largely impedes the development of such document-level MT systems. This paper proposes to(More)
Long-distance semantic dependencies are crucial for lexical choice in statistical machine translation. In this paper, we study semantic dependencies between verbs and their arguments by modeling selectional preferences in the context of machine translation. We incorporate preferences that verbs impose on subjects and objects into translation. In addition,(More)
In gender classification, labeled data is often limited while unlabeled data is ample. This motivates semi-supervised learning for gender classification to improve the performance by exploring the knowledge in both labeled and unlabeled data. In this paper, we propose a semi-supervised approach to gender classification by leveraging textual features and a(More)
Tense of one sentence can indicate the time when an event takes place. Therefore, it is very useful for natural language processing tasks such as Machine Translation (MT). However, the mapping of tense in MT is a very challenging problem as the usage of tenses varies from one language to another. Aiming at translating one language (source) which lacks overt(More)