• Corpus ID: 6236390

Applying Textual Case-based Reasoning and Information Extraction in Lessons Learned Systems

  title={Applying Textual Case-based Reasoning and Information Extraction in Lessons Learned Systems},
  author={Kevin D. Ashley},
Textual Case-Based Reasoning and Information Extraction may assist in constructing Lessons Learned Systems where the lessons are texts. For a particular lesson domain, developers first should identify the kinds of information needed to compare lessons. Information Extraction techniques may then be applied in at least three ways to help extract such information automatically from lesson texts. 

Figures from this paper

Semi-automatic generation of ontologies for knowledge-intensive CBR
This work examines how automatic generation of general domain knowledge from text can contribute to the knowledge intensive Case-Based Reasoning (CBR) system, Creek. This will be done by combining
Representing and Retrieving Knowledge Artifacts
The retrieval method presented is designed to benefit from the representational structure and provides guidance to users on how many terms to enter when creating a query to search for knowledge artifacts.
Intelligent lessons learned systems
Categorizing Intelligent Lessons Learned Systems
A two-step categorization method is proposed to support the design of intelligent lessons learned systems and identify some pertinent research directions that may benefit from applying artificial intelligence (AI) techniques.
Categorizing Intelligent Lessons Learned Systems 1
This paper proposes a two-step categorization method to support the design of intelligent lessons learned systems and identifies some pertinent research directions that may benefit from applying artificial intelligence (AI) techniques.
Case Representation and Similarity Assessment in a Recommender System to Support Dementia Caregivers in Geriatric and Palliative Care
The purpose of this research is to develop a CBR system for recommending the related references by using the information retrieved from dementia books based on the ICF framework of WHO.


What You Saw Is What You Want: Using Cases to Seed Information Retrieval
This paper presents a hybrid case-based reasoning (CBR) and information retrieval (IR) system, called SPIRE, that both retrieves documents from a full-text document corpus and from within individual
Bootstrapping Case Base Development with Annotated Case Summaries
Experimental results which indicate the usefulness of learning from sentences and adding a thesaurus are presented, and the chances and limitations of leveraging the learned classifiers for full-text documents are considered.
Automatically Generating Extraction Patterns from Untagged Text
  • E. Riloff
  • Computer Science
    AAAI/IAAI, Vol. 2
  • 1996
This work has developed a system called AutoSlog-TS that creates dictionaries of extraction patterns using only untagged text, and in experiments with the MUG-4 terrorism domain, created a dictionary of extraction pattern that performed comparably to a dictionary created by autoSlog, using only preclassified texts as input.
Teaching case-based argumentation through a model and examples
It is a novel result that students can learn basic argumentation skills by studying computer-generated examples, which means that an instructional system does not necessarily need to rely on a very sophisticated understanding of students' arguments, which would be a significant obstacle to developing such systems.
Question Answering from Frequently Asked Question Files: Experiences with the FAQ FINDER System
This technical report describes FAQ Finder, a natural language question answering system that uses files of frequently asked questions as its knowledge base, and describes the design and the current implementation of the system and its support components.
Automatically Constructing a Dictionary for Information Extraction Tasks
Using AutoSlog, a system that automatically builds a domain-specific dictionary of concepts for extracting information from text, a dictionary for the domain of terrorist event descriptions was constructed in only 5 person-hours and the overall scores were virtually indistinguishable.
What Is Case-Based Reasoning?
Reasoning Symbolically About Partially Matched Cases
The answer lies in heuristic policies embodied in CATO's algorithm for emphasizing a distinction, which ensure that a sufficient contrast between the cases exists, with respect to both the focal abstraction itself and its ancestors in the Hierarchy.
QuestionAnswering from Frequently-Asked Question Files: Experiences with the FAQ FINDER
  • 1997
CBR for Document Retrieval: The FAIlQ Project In CBR Res. and Devel
  • Proc. 2d Int'l Conf. on CBR,. ICCBR-97. 84-93. Lecture Notes in AI Series No. 1266
  • 1997