The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper presents a training method of log-linear model for statistical machine translation based on structural support vector machine. This method is designed to directly optimize parameters with respect to translation quality. By adopting maximum-margin principle of SVM, the MT model can learn from training samples with generalization capability. Experiments are carried out on a hierarchical phrase-based...
Automatic speech processing systems are employed more and more often in real environments. However, they are confronted with high ambient noise levels and their performance degrades drastically. An robust and practical speech recognition system using integrating feature and Hidden Markov Model(HMM) was proposed aiming at improving speech recognition rate in noise environmental conditions. It integrated...
This paper presents a novel application of incorporating Alternating Structure Optimization (ASO) to conduct the task of text chunking of Semantic Role Labeling (SRL) in Chinese texts. ASO is a competent linear algorithm based on the theory of multi-task learning. In this paper, by constructing several SRL tasks to constitute a multi-task, we are able to encode the inference obtained by ASO algorithm...
The article discusses methods of improving the ways of applying balanced random forests (BRFs), a machine learning classification algorithm, used to extract definitions from written texts. These methods include different approaches to selecting attributes, optimising the classifier prediction threshold for the task of definition extraction and initial filtering by a very simple grammar.
An improved TBL based post-processing approach is proposed for Japanese named entity recognition (NER) in this paper. Firstly, tuning rules are automatically acquired from the results of Japanese NER by error-driven learning. And then, the tuning rules are optimized according to given threshold conditions. After filtered, the rules are used to revise the results of Japanese NER. Above all, this approach...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.