This paper shows how syntactic neural networks may be applied to the problem of translating orthographic strings to phonetics strings, and vice versa, due to the symmetry of the model. Note that this is unusual in text-phonetics translation systems; most systems have to be trained to operate in a single direction. Another novel feature is the lack of supervision required during training. The only requirement is that we have whole-word orthographic/phonetic symbolstring pairs. To test the system, we have formed a lexicon of (6,000, single-syllable)' such pairs in English by extracting the relevant information from the machine-readable Oxford Advanced Learner's Dictionary. Results are presented for cases where the training set varies between 10 and 2000 words. In each case, the trained nets are tested on the training set and an equal size (disjoint) test-set.
This paper presents a environment using the eXtensible Markup Language ,XML, to describe a robotic systems in a format suitable for simulation, and to support the integration of several programming environments to create a flexible physical simulation system. Data exchange via open-standard based plain text files allows the system components to be loosely-coupled, rather than combined them into a single integrated development environment. This ensures that the most appropriate tools can be used for each component and the system can be extended with minimal disruption. Those parts of the system that require real-time data exchange use simple UNIX socket-based interactions, which are configured using shared XML configuration files. The environment is demonstrated by the simulation of a simple task using a SCARA robot.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.