Minimum Error Rate Training (MERT) as an effective parameters learning algorithm is widely applied in machine translation and system combination area. However, there exists an ambiguity problem in respect to the train...
详细信息
In order to improve the accuracy of the image annotation, an automatic image annotation method based on mutual K-nearest neighbor graph(MKNN) is proposed. The peoposed algorithm describes the relationship between low-...
详细信息
We propose a structure called dependency forest for statistical machine translation. A dependency forest compactly represents multiple dependency trees. We develop new algorithms for extracting string-to dependency ru...
详细信息
We propose a structure called dependency forest for statistical machine translation. A dependency forest compactly represents multiple dependency trees. We develop new algorithms for extracting string-to dependency rules and training dependency language models. Our forest-based string-to-dependency system obtains significant improvements ranging from 1.36 to 1.46 BLEU points over the tree-based baseline on the NIST 2004/2005/2006 Chinese-English test sets.
The Dempster-Shafer (D-S) evidence theory is widely used in many fields of information fusion. However, counter-intuitive results may be obtained by the classical Dempster combination rule when collected evidences are...
详细信息
As tokenization is usually ambiguous for many natural languages such as Chinese and Korean, tokenization errors might potentially introduce translation mistakes for translation systems that rely on 1-best tokenization...
详细信息
As tokenization is usually ambiguous for many natural languages such as Chinese and Korean, tokenization errors might potentially introduce translation mistakes for translation systems that rely on 1-best tokenizations. While using lattices to offer more alternatives to translation systems have elegantly alleviated this problem, we take a further step to tokenize and translate jointly. Taking a sequence of atomic units that can be combined to form words in different ways as input, our joint decoder produces a tokenization on the source side and a translation on the target side simultaneously. By integrating tokenization and translation features in a discriminative framework, our joint decoder outperforms the baseline translation systems using 1-best tokenizations and lattices significantly on both Chinese- English and Korean-Chinese tasks. Interestingly, as a tokenizer, our joint decoder achieves significant improvements over monolingual Chinese tokenizers.
In order to improve the efficiency of service discovery in the pervasive environment, this paper presents a new strategy of service discovery based on p2p network model. Reference the ring topology of chord algorithm ...
详细信息
ISBN:
(纸本)9780955529337
In order to improve the efficiency of service discovery in the pervasive environment, this paper presents a new strategy of service discovery based on p2p network model. Reference the ring topology of chord algorithm and tbe algorithm used by DDT, tbe traditional single finger-table witch be maintained by each node in the ring will be changed into double finger-table: the Neigbbor-Finger-Table and Long-distance Finger-Table. The structure of the Neighbor-Finger-Table is the same as the traditional single finger-table's. The Long-distance Finger-Table can construct small-world network. Some similar algorithm uses random method to select remote access node, the new strategy is different from that, tbrough tbe calculation of the local node, it can ensure the scope of service can cover tbe entire network. The simulation shows the algorithm can effectively reduce the path length of service discovery, improve the service success rate, and control the path length of magnitude.
In pervasive computing paradigm, the image data obtained by a variety of multimedia, information equipment. In order to make use of these information reasonably and efficiently, a new method for image fusion based on ...
详细信息
ISBN:
(纸本)9780955529337
In pervasive computing paradigm, the image data obtained by a variety of multimedia, information equipment. In order to make use of these information reasonably and efficiently, a new method for image fusion based on fuzzy neural network has presented in this paper. It can fuse massive data from the multi-sensor image. Here, fuzzy neural network is a paraDel information processing model, there are more adaptive and self-organization, and can accomplish the complexity of real-time computing and mass data retrieval, it demonstrate its unique superiority of image understanding, pattern recognition and the handling of incomplete information. The fuzzy neural network system developed by us can be used in multi- sensor image fusion. Based on our experiments, it has been proved that the fusion is fast, effective, and can meet the real-time requirements of pervasive computing.
A novel Weighted Graph Partitioning Active Contours method based on weighted dissimilarity is introduced. This method is easy to be extended by defining different types of similarities. And it has been greatly acceler...
详细信息
We propose a novel method to improve the training efficiency and accuracy of boosted classifiers for object detection. The key step of the proposed method is a sample pre-mapping on original space by referring to the ...
详细信息
This paper presents a new method to detect pedestrian in still image using Sigma sets as image region descriptors in the boosting framework. Sigma set encodes second order statistics of an image region implicitly in t...
详细信息
暂无评论