Page: 1 2 3 4 5 6 7 8 9 10
82 |
Reading to Learn
|
|
|
|
In: DTIC (2006)
|
|
Abstract:
One of the most important methods by which human beings learn is by reading, a task that includes integrating what was read with existing, prior knowledge. While in its full generality, the reading task is still too difficult a capability to be implemented in a computer, significant (if partial) approaches to the task are now feasible. Our goal in this project was to study issues and develop solutions for this task by working with a reduced version of the problem, namely working with text written in a simplified version of English (a Controlled Language) rather than full natural language. Our experience and results reveal that even this reduced version of the task is still challenging, and we have uncovered several major insights into this challenge. We describe our work and analysis, present a synthesis and evaluation of our work, and make several recommendations for future work in this area. Our conclusion is that ultimately, to bridge the "knowledge gap", a pipelined approach is inappropriate, and that to address the knowledge requirements for good language understanding an iterative (bootstrapped) approach is the most promising way forward. ; Prepared in cooperation with Boeing Company, Seattle, WA. The original document contains color images.
|
|
Keyword:
*ARTIFICIAL INTELLIGENCE; *CPL(COMPUTER-PROCESSABLE LANGUAGE); *KNOWLEDGE GAP; *LEARNING MACHINES; *READING; BOOTSTRAPPING; CL(CONTROLLED LANGUAGE); COMPUTER LOGIC; Computer Programming and Software; Cybernetics; KNOWLEDGE BASES; Linguistics; NATURAL LANGUAGE; READING TO LEARN; REASONING
|
|
URL: http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA456285 http://www.dtic.mil/docs/citations/ADA456285
|
|
BASE
|
|
Hide details
|
|
85 |
Towards Collaboration with Robots in Shared Space: Spatial Perspective and Frames of Reference
|
|
|
|
In: DTIC (2005)
|
|
BASE
|
|
Show details
|
|
87 |
Human Language Technology: Opportunities and Challenges
|
|
|
|
In: DTIC (2005)
|
|
BASE
|
|
Show details
|
|
89 |
Una aproximación multilingüe a la clasificación de preguntas basada en aprendizaje automático
|
|
|
|
BASE
|
|
Show details
|
|
90 |
Automatic text categorisation of racist webpages
|
|
Greevy, Edel. - : Dublin City University. School of Computing, 2004
|
|
In: Greevy, Edel (2004) Automatic text categorisation of racist webpages. Master of Science thesis, Dublin City University. (2004)
|
|
BASE
|
|
Show details
|
|
91 |
Analysis of Statistical Question Classification for Fact-based Questions
|
|
|
|
In: http://ciir.cs.umass.edu/pubfiles/ir-323.pdf (2004)
|
|
BASE
|
|
Show details
|
|
92 |
Semantic Lexicon Construction: Learning from Unlabeled Data via Spectral Analysis
|
|
|
|
In: DTIC (2004)
|
|
BASE
|
|
Show details
|
|
93 |
Semantic Role Labeling via Integer Linear Programming Inference
|
|
|
|
In: DTIC (2004)
|
|
BASE
|
|
Show details
|
|
94 |
Learning to Identify TV News Monologues by Style and Context
|
|
|
|
In: DTIC (2003)
|
|
BASE
|
|
Show details
|
|
95 |
Linguistic Resource Creation for Research and Technology Development: A Recent Experiment
|
|
|
|
In: DTIC (2003)
|
|
BASE
|
|
Show details
|
|
96 |
Word-level Alignment for Multilingual Resource Acquisition
|
|
|
|
In: DTIC (2002)
|
|
BASE
|
|
Show details
|
|
97 |
Early Pragmatic Language Development for an Infant Robot
|
|
|
|
In: DTIC (2002)
|
|
BASE
|
|
Show details
|
|
100 |
Intelligent Record Linkage Techniques Based on Information Retrieval, Natural Language Processing, and Machine Learning
|
|
|
|
In: DTIC AND NTIS (2002)
|
|
BASE
|
|
Show details
|
|
Page: 1 2 3 4 5 6 7 8 9 10
|
|