The Experts below are selected from a list of 294 Experts worldwide ranked by ideXlab platform
Giuseppe Di Fabbrizio - One of the best experts on this subject based on the ideXlab platform.
-
Where do the words come from? learning models for word choice and ordering from spoken dialog corpora
ICASSP IEEE International Conference on Acoustics Speech and Signal Processing - Proceedings, 2008Co-Authors: Amanda J. Stent, Srinivas Bangalore, Giuseppe Di FabbrizioAbstract:Most existing generation Systems for spoken dialog require the System Engineer to specify by hand the words to be used in System prompts. However, the existence of corpora of spoken dialog makes it possible to acquire the words and structure of System prompts automatically. In this paper, we construct statistical models for generating System prompts, both for word choice and for word ordering. We evaluate these models using a human-computer dialog multicorpus and a human-human dialog corpus. Our results show that statistical models for word choice can work well, while more work is needed on statistical models for word ordering. ©2008 IEEE.
-
Where do thewords come from? Learning models for word choice and ordering from spoken dialog corpora
2008 IEEE International Conference on Acoustics Speech and Signal Processing, 2008Co-Authors: Amanda J. Stent, Srinivas Bangalore, Giuseppe Di FabbrizioAbstract:Most existing generation Systems for spoken dialog require the System Engineer to specify by hand the words to be used in System prompts. However, the existence of corpora of spoken dialog makes it possible to acquire the words and structure of System prompts automatically. In this paper, we construct statistical models for generating System prompts, both for word choice and for word ordering. We evaluate these models using a human-computer dialog multicorpus and a human-human dialog corpus. Our results show that statistical models for word choice can work well, while more work is needed on statistical models for word ordering.
Amanda J. Stent - One of the best experts on this subject based on the ideXlab platform.
-
Where do the words come from? learning models for word choice and ordering from spoken dialog corpora
ICASSP IEEE International Conference on Acoustics Speech and Signal Processing - Proceedings, 2008Co-Authors: Amanda J. Stent, Srinivas Bangalore, Giuseppe Di FabbrizioAbstract:Most existing generation Systems for spoken dialog require the System Engineer to specify by hand the words to be used in System prompts. However, the existence of corpora of spoken dialog makes it possible to acquire the words and structure of System prompts automatically. In this paper, we construct statistical models for generating System prompts, both for word choice and for word ordering. We evaluate these models using a human-computer dialog multicorpus and a human-human dialog corpus. Our results show that statistical models for word choice can work well, while more work is needed on statistical models for word ordering. ©2008 IEEE.
-
Where do thewords come from? Learning models for word choice and ordering from spoken dialog corpora
2008 IEEE International Conference on Acoustics Speech and Signal Processing, 2008Co-Authors: Amanda J. Stent, Srinivas Bangalore, Giuseppe Di FabbrizioAbstract:Most existing generation Systems for spoken dialog require the System Engineer to specify by hand the words to be used in System prompts. However, the existence of corpora of spoken dialog makes it possible to acquire the words and structure of System prompts automatically. In this paper, we construct statistical models for generating System prompts, both for word choice and for word ordering. We evaluate these models using a human-computer dialog multicorpus and a human-human dialog corpus. Our results show that statistical models for word choice can work well, while more work is needed on statistical models for word ordering.
Srinivas Bangalore - One of the best experts on this subject based on the ideXlab platform.
-
Where do the words come from? learning models for word choice and ordering from spoken dialog corpora
ICASSP IEEE International Conference on Acoustics Speech and Signal Processing - Proceedings, 2008Co-Authors: Amanda J. Stent, Srinivas Bangalore, Giuseppe Di FabbrizioAbstract:Most existing generation Systems for spoken dialog require the System Engineer to specify by hand the words to be used in System prompts. However, the existence of corpora of spoken dialog makes it possible to acquire the words and structure of System prompts automatically. In this paper, we construct statistical models for generating System prompts, both for word choice and for word ordering. We evaluate these models using a human-computer dialog multicorpus and a human-human dialog corpus. Our results show that statistical models for word choice can work well, while more work is needed on statistical models for word ordering. ©2008 IEEE.
-
Where do thewords come from? Learning models for word choice and ordering from spoken dialog corpora
2008 IEEE International Conference on Acoustics Speech and Signal Processing, 2008Co-Authors: Amanda J. Stent, Srinivas Bangalore, Giuseppe Di FabbrizioAbstract:Most existing generation Systems for spoken dialog require the System Engineer to specify by hand the words to be used in System prompts. However, the existence of corpora of spoken dialog makes it possible to acquire the words and structure of System prompts automatically. In this paper, we construct statistical models for generating System prompts, both for word choice and for word ordering. We evaluate these models using a human-computer dialog multicorpus and a human-human dialog corpus. Our results show that statistical models for word choice can work well, while more work is needed on statistical models for word ordering.
R.c. Moore - One of the best experts on this subject based on the ideXlab platform.
-
Characteristics of a successful space System Engineer
IEEE Aerospace and Electronic Systems Magazine, 2000Co-Authors: R.c. MooreAbstract:The Far Ultraviolet Spectroscopic Explorer (FUSE) satellite was launched on June 24, 1999, on a three-year mission to explore the universe using the technique of high-resolution spectroscopy in the far-ultraviolet spectral region. The FUSE instrument comprises many subSystems, each of which contributes in an essential way to the success of the mission. The instrument System Engineer oversees the Engineering of all elements in such a complex technical project. In performing System Engineering for the FUSE instrument's command, telemetry, data processing and data storage functions, and in leading the Engineering efforts for the development of the FUSE instrument on-board computer, the author has learned valuable lessons about the characteristics that are prerequisite to success for a space System Engineer. These characteristics fall under various categories of acquired, practical know-how. These categories are described with illustrations drawn from the development of the FUSE instrument. In addition to these practical skills and the concomitant knowledge, the System Engineer needs personal integrity, which is the link that connects knowledge with know-how and makes them work together to motivate a team of subSystem Engineers. This, too, will be discussed.
-
Characteristics of a successful space System Engineer
Gateway to the New Millennium. 18th Digital Avionics Systems Conference. Proceedings (Cat. No.99CH37033), 1999Co-Authors: R.c. MooreAbstract:The technique of high-resolution spectroscopy in the far-ultraviolet spectral region, FUSE will be one of the most far-reaching scientific explorations of space to date. The FUSE instrument comprises many subSystems, each of which contributes in on essential way to the success of the mission. The instrument System Engineer oversees the Engineering of all elements in such a complex technical project. In performing System Engineering for the FUSE instrument's command, telemetry, data processing and data storage functions, and in leading the Engineering efforts for the development of the FUSE instrument on-board computer, the author has learned valuable lessons about the characteristics that are prerequisite to success for a space System Engineer. The categories of know-how which fall into seven areas are described with illustrations drawn from the development of the FUSE instrument.
J V Milanovic - One of the best experts on this subject based on the ideXlab platform.
-
towards application of text mining for enhanced power network data analytics part ii offline analysis of textual data
Mediterranean Conference on Power Generation Transmission Distribution and Energy Conversion (MedPower 2016), 2016Co-Authors: Yushi Chen, Jelena Ponocko, Nikola Milosevic, Goran Nenadic, J V MilanovicAbstract:Text mining is a subdivision of data mining technologies used to extract useful information from unstructured textual data. In recent years, power distribution networks have become more complex due to the versatile consumer demand and integration of distributed energy resources. This has led to the need for enhanced data processing and analysis, i.e., data analytics, in distribution System studies. This paper for the first time explores the feasibility of application of text mining methods as a part of power System data analytics. The focus is on identifying and describing the steps that need to be taken for the knowledge extraction from large offline textual document collections and on demonstrating the effectiveness of the whole process if undertaken by a power System Engineer, i.e., a nonspecialist in the area of text mining.
-
Towards application of text mining for enhanced power network data analytics — Part II: Offline analysis of textual data
Mediterranean Conference on Power Generation Transmission Distribution and Energy Conversion (MedPower 2016), 2016Co-Authors: Yushi Chen, Jelena Ponocko, Nikola Milosevic, Goran Nenadic, J V MilanovicAbstract:Text mining is a subdivision of data mining technologies used to extract useful information from unstructured textual data. In recent years, power distribution networks have become more complex due to the versatile consumer demand and integration of distributed energy resources. This has led to the need for enhanced data processing and analysis, i.e., data analytics, in distribution System studies. This paper for the first time explores the feasibility of application of text mining methods as a part of power System data analytics. The focus is on identifying and describing the steps that need to be taken for the knowledge extraction from large offline textual document collections and on demonstrating the effectiveness of the whole process if undertaken by a power System Engineer, i.e., a nonspecialist in the area of text mining.
