This paper presents a description for the ICT systems involved in the IWSLT 2008 evaluation campaign. This year, we participated in Chinese-English and English-Chinese translation directions. Four statistical machine ...
详细信息
Hyper Surface Classification (HSC) is a novel classification method based on hyper surface which is put forward by Qing He, etc. Experiments show that HSC can efficiently and accurately classify large-size data in two...
详细信息
Hyper Surface Classification (HSC) is a novel classification method based on hyper surface which is put forward by Qing He, etc. Experiments show that HSC can efficiently and accurately classify large-size data in two dimensional space and three-dimensional space. Actually, it is difficult to deal with high dimensional data for HSC. So the dimension reduction (data rearrangement) and ensemble methods (feature subspace) are proposed for HSC. But the method based on ensemble will produce many inconsistent and repetitious data in some density dataset, which influence the classification ability of HSC. To solve the problem, a simple and effective kind of data feature transformation method for enhancing performance of HSC is proposed in this paper. The experimental results show that this method can efficiently reduce the inconsistent and repetitious data, efficiently utilize the data information, and remarkably improve the classification performance of HSC.
Large scale video copy detection task requires compact feature insensitive to various copy changes. Based on local feature trajectory behavior we discover invariant visual patterns for generating robust feature. Bag o...
详细信息
This paper presents a partial matching strategy for phrase-based statistical machine translation (PBSMT). Source phrases which do not appear in the training corpus can be translated by word substitution according to p...
详细信息
Dynamic description logic (DDL) is among the few emerging service composition solutions through logical reasoning. To overcome low efficiency and lacking context-aware support of DDL reasoning, we propose a new DDL-ba...
详细信息
Video copy detection is essentially a problem of large scale pattern matching. Various copy attacks which change the visual appearance impose hazard on this task. Based on the spatio-temporal consistency, our algorith...
详细信息
Firstly, a new Clustering algorithm based on Hyper Surface (CHS) is put forward in this paper. CHS needs no domain knowledge to determine input parameters. However, it is difficult to process locally dense data for CH...
详细信息
This paper proposes a novel maximum entropy based rule selection (MERS) model for syntax-based statistical machine translation (SMT). The MERS model combines local contextual information around rules and information o...
详细信息
This paper proposes a novel lexicalized approach for rule selection for syntax-based statistical machine translation (SMT). We build maximum entropy (MaxEnt) models which combine rich context information for selecting...
详细信息
This paper presents a partial matching strategy for phrase-based statistical machine translation (PBSMT). Source phrases which do not appear in the training corpus can be translated by word substitution according to p...
详细信息
暂无评论