In image/video processing software and hardware products, low complexity interpolation algorithms, such as cubic and splines methods, are commonly used. However, these methods tend to blur textures and produce jaggy e...
详细信息
SVM (Support Vector Machines) is a novel algorithm of machine learning which is based on SLT (Statistical Learning Theory). It can solve the problem characterized by nonlinear, high dimension, small sample and local m...
详细信息
How to reduce the amount of relevance judgments is an important issue in retrieval evaluation. In this paper, we propose a novel method using global statistics to rank retrieval systems without relevance judgments. In...
详细信息
Fast stereoscopic video encoding becomes a highly desired technique because the stereoscopic video has been realizable for applications like TV broadcasting and consumer electronics. The stereoscopic video has high in...
详细信息
Data space is a semi-structural data model for the management of large-scale heterogeneous data objects. In a data space, each data object consists of a set of attribute-value pairs to describe the internal properties...
详细信息
As the Web continues to grow, the pornographic texts in varied forms run rampant on Internet, despite repeated prohibitionsm. It severely does harms to the development of people's mental health and the stability o...
详细信息
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
This paper tries to fill the gap between Traditional Chinese Pulse Diagnosis (TCPD) and Doppler diagnosis by applying digital signal analysis and pattern classification techniques to wrist radial arterial Doppler bloo...
详细信息
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 alleviate this probl...
详细信息
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 alleviate this problem, we use compact structures, lattice and forest, in each module instead of 1-best results. We integrate both lattice and forest into a single tree-to-string system, and explore the algorithms of lattice parsing, lattice-forest-based rule extraction and decoding. More importantly, our model takes into account all the probabilities of different steps, such as segmentation, parsing, and translation. The main advantage of our model is that we can make global decision to search for the best segmentation, parse-tree and translation in one step. Medium-scale experiments show an improvement of +0.9 BLEU points over a state-of-the-art forest-based baseline.
Parsing plays an important role in semantic role lab.ling (SRL) because most SRL systems infer semantic relations from I-best parses. Therefore, parsing errors inevitably lead to lab.ling mistakes. To alleviate this p...
详细信息
暂无评论