| A Context, Role, and Semantics Based Approach for Countering Malicious Insider Threats
|
| Development of a Semantic Analysis Monitor to measure the extent to which incoming and outgoing communications as well as documents accessed and produced are appropriate for the assigned task of technical analysts. |
|
Adaptive Interactive Discovery Environment (AIDE): A Revolutionary Learning Environment (NASA)
AT&T Extension of the AIDE Project
Army Extension of the AIDE Project
Next Steps in the Knowledge Acquisition and Access System (KAAS)
|
| Jointly-funded, a specialization of CNLP’s generic question-answering system for a collaborative learning environment for use by aerospace engineering students. Includes extensive evaluation of the usability and understandability. |
|
| Computer-Assisted Content Standard Assignment & Alignment (CASAA)
|
| Development and evaluation of a methodology and tool to produce an automated mapping between all state educational standards, whereby national standards function as the “exchange standard” through which any state standard can be mapped to any other state standard so that teachers can search for resources using their home state standards. For more information, see CAT and SAT. |
|
| Cross-Language Information Exploitation of Arabic
|
| Research and development of a generalizable methodology for producing cross-lingual information retrieval systems that will support users who have minimal understanding of the languages of the documents they need to search. First implemented in Arabic. |
|
| DHB: Investigating the Dynamics of Free/Libre Open Source Software Development Teams
|
| The team will be investigating the dynamics through which Free/Libre Open Source Software (FLOSS) teams develop shared mental models and the norms and rules for interaction and work processes. Three methods to investigate these processes will be integrated: natural language processing, social network analysis, and source code analysis. |
|
| Improving Public Health Grey Literature Access for the Public Health Workforce
|
| The broad, long-term objective of this project is to provide the public health workforce with improved access to high quality, highly relevant public health grey literature reports, based on the premise that such access has the potential to positively impact the quality, effectiveness, and efficiency of planning, conducting, and evaluating public health interventions.
Our goals are to extend, test, and evaluate a public health grey literature information system. The research consists of two components – 1) continuation of a user-focused technical system development, and 2) evaluations of this system on the tasks of the public health workforce in county health agencies.
The technical system is a web-based system that gathers and mounts a collection of high quality grey literature reports, that is easily updated and tailored for specific needs, and is searchable through natural language, free text queries or a fill-in-the-blanks form. Results will display quick summaries – rich representations of the essential information elements contained in these reports using Natural Language Processing (NLP) based on the validated model of public health intervention reports from our earlier Robert Wood Johnson funded basic research project. Sufficient informativeness of the document summaries produced by the system will enable accurate selection by the public health workforce of full reports for further review.
|
|
Intelligent Information Retrieval and Extraction using Natural Language Processing
Adaptation Software for Domain-Specific Environments
LiVIA Phase III
|
| Development and demonstration of an innovative Text Mining and Knowledge Discovery prototype software application aimed at the increasing demand for information, structure, and usability by the defense and intelligence communities. |
|
| TEGO
|
| The objective of TEGO is to “facilitate multi-domain operations (e.g., coalitions) via disclosure analysis tools able to process free text information and establish/present new rich metadata entries based on meaning.” That is, TEGO will analyze text messages between US and foreign coalition personnel to detect disclosure—perhaps unintentional—of sensitive information to generate an alert for a human decision maker (i.e., a Foreign Disclosure Officer or FDO). This technology will be based on CNLP’s graph knowledge representation structure, integrated with 21st Century’s TMODS graph pattern matching algorithm. |
|
| Understanding the Connotative Meaning of Text
|
Our mission is to develop and test Natural Language Processing capabilities that can recognize, interpret, and characterize implicit levels of meaning in text without requiring human intervention, a substantial step forward in natural language understanding that would offer tremendous advantages to all its applications.
In order to accomplish this goal, we have undertaken a two-phased approach. The first is to conduct human subject experiments to better understand and model human ability to recognize the more subtle aspects of messages, and the second, based on these new understandings, is to apply Machine Learning algorithms to enable a system to accomplish this fully automatically.
The initial corpus of analysis is blogs, an unconventional, highly-personalized genre, and the initial application is Question-Answering, where our hypothesis is that the recognition of connotative meaning can contribute to richer / more subtle question-answering systems.
|
|
