| Rapidly Customizable Spoken Dialogue Systems |
28-Jan-2009 |
12 pages |
| Authors:
James Allen; FLORIDA INSTITUTE FOR HUMAN AND MACHINE COGNITION INC PENSACOLA FL
|
 | Building a robust spoken dialogue system for a new application, task, or domain currently requires considerable effort, including substantial efforts in data collection, building language models, grammar/parser development, building a custom dialogue manager, and developing the connection to the system's back-end systems (e.g., a database query or knowledge based system). This project developed key parts of a technology base upon which spoken dialogue systems can be rapidly constructed for new ... |
|
| Naval Automation and Information Management Technology |
03 JAN 2006 |
46 pages |
| Authors:
Jerry Pratt; Jeffrey M. Bradshaw; James Allen; Lucian Galescu; Niranjan Suri; FLORIDA INSTITUTE FOR HUMAN AND MACHINE COGNITION INC PENSACOLA FL
|
| In future military scenarios, large numbers of unmanned ground, air, underwater, and surface vehicles will work together, coordinated by an ever smaller number of human operators. In order to be operationally efficient, effective and useful, these robots must have competent physical and sensing abilities, must be able to perform complex tasks semi-autonomously, must be able to coordinate with each other, and must ultimately be observable and controllable in a useful ... |
|
| Semantics, Dialogue, and Reference Resolution |
2006 |
8 pages |
| Authors:
Joel Tetreault; James Allen; ROCHESTER UNIV NY DEPT OF COMPUTER SCIENCE
|
| Most pronoun resolution research has focused on written corpora while using syntactical and surface cues. Though big gains have been made in this domain with those methods, it is difficult to do better than the 80% coverage in these domains without some world or semantic knowledge. We investigate this issue by incorporating rich semantic information into a proven reference resolution model over a very difficult domain of human-human task-oriented dialogues. ... |
|
| Skeletons in the Parser: Using a Shallow Parser to Improve Deep Parsing |
AUG 2004 |
8 pages |
| Authors:
Mary Swift; James Allen; Daniel Gildea; ROCHESTER UNIV NY DEPT OF COMPUTER SCIENCE
|
| We describe a simple approach for integrating shallow and deep parsing. We use phrase structure bracketing obtained from the Collins parser as filters to guide deep parsing. Our experiments demonstrate that our technique yields substantial gains in speed along with modest improvements in accuracy. |
|
| Incremental Parsing with Reference Interaction |
JUL 2004 |
9 pages |
| Authors:
Scott C. Stoness; Joel Tetreault; James Allen; ROCHESTER UNIV NY DEPT OF COMPUTER SCIENCE
|
| We present a general architecture for incremental interaction between modules in a speech-to-intention continuous understanding dialogue system. This architecture is then instantiated in the form of an incremental parser which receives suitability feedback on NP constituents from a reference resolution module. Oracle results indicate that perfect NP suitability judgments can provide a labelled-bracket error reduction of as much as 42% and an efficiency improvement of 30%. Preliminary experiments in which ... |
|
| Stochastic Language Generation in a Dialogue System: Toward a Domain Independent Generator |
2004 |
11 pages |
| Authors:
Nathanael Chambers; James Allen; FLORIDA INSTITUTE FOR HUMAN AND MACHINE COGNITION INC PENSACOLA FL
|
| Until recently. surface generation in dialogue systems has served the purpose of simply providing a backend to other areas of research. The generation component of such systems usually consists of templates and canned text, providing inflexible, unnatural output. To make matters worse, the resources are typically specific to the domain in question and not portable to new tasks. In contrast, domain-independent generation systems typically require large grammars, full lexicons, complex ... |
|
Reports by Author
