Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

Simon Fraser University

$23,000.00

Information extraction with knowledge-based linguistic analysis

FY 2006-07

Summary
With the ever increasing amount of on-line textual information available to individuals and organizations in numerous languages, it is becoming even more important to provide better techniques to manage, retrieve and analyze this text.  While a wide range of techniques have already been developed that allow computers to automatically detect patterns and relationships, tasks involving the processing of human languages can benefit from additional knowledge relevant for the domain in question, and general knowledge about language and its use. The proposed research will deal with fundamental issues in natural language processing research, examining how linguistic and domain knowledge can be applied to improve the performance and maintainability of applications that make use of information extraction. In dealing with this long term goal, the key short-term objectives will include the development and evaluation of algorithms and resources for the following tasks: 1. anaphora resolution - specifically, techniques to determine the named entity associated with an occurrence of a pronoun like "he", "she" or "it" in a text, as required by information retrieval and information extraction applications 2. Automatic and semi-automatic construction of linguistic and domain-dependent knowledge resources, with an initial focus on medical texts, and algorithms that can be used for information extraction and information retrieval 3. Automatic and semi-automatic construction of multi-lingual resources for information extraction and retrieval, with an initial focus on English and French, and development of algorithms for evaluating the effectiveness of these resources
Program
Discovery Grants Program - Individual
Location
British Columbia, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
41910-2006
Name nom
Popowich, Frederick
Department département
Computing Science
Organization id
5
Institution établissement
Simon Fraser University
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2006
Competition year année de concours
2006
Award amount
23000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
331
Committee name en
Computing and Information Sciences - B
Committee name fr
Informatique - B
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
Research subject code
2801
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Natural language and speech understanding
Research subject fr
Langage naturel et reconnaissance de la parole
Partie
1
Nb partie
5
Application title
Information extraction with knowledge-based linguistic analysis
Keyword
NA
Application summary
With the ever increasing amount of on-line textual information available to individuals and organizations in numerous languages, it is becoming even more important to provide better techniques to manage, retrieve and analyze this text.  While a wide range of techniques have already been developed that allow computers to automatically detect patterns and relationships, tasks involving the processing of human languages can benefit from additional knowledge relevant for the domain in question, and general knowledge about language and its use. The proposed research will deal with fundamental issues in natural language processing research, examining how linguistic and domain knowledge can be applied to improve the performance and maintainability of applications that make use of information extraction. In dealing with this long term goal, the key short-term objectives will include the development and evaluation of algorithms and resources for the following tasks: 1. anaphora resolution - specifically, techniques to determine the named entity associated with an occurrence of a pronoun like "he", "she" or "it" in a text, as required by information retrieval and information extraction applications 2. Automatic and semi-automatic construction of linguistic and domain-dependent knowledge resources, with an initial focus on medical texts, and algorithms that can be used for information extraction and information retrieval 3. Automatic and semi-automatic construction of multi-lingual resources for information extraction and retrieval, with an initial focus on English and French, and development of algorithms for evaluating the effectiveness of these resources