Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

University of Ottawa

$17,000.00

Natural language processing for speech information retrieval and computer-assisted language learning

FY 2009-10

Summary
Existing search engines allow a user to retrieve useful information from texts on the Internet, but not from audio documents such as broadcast news or other recordings. The user has to browse through long audio recordings to find relevant parts. Despite much progress both in commercial applications and in research prototypes that deal with natural language, their performance of information retrieval systems still needs to be improved. We propose new ways of combining symbolic and statistical methods for dealing with the meaning of words and sentences. We plan to apply them in several tasks where they have not yet been tried. In particular, we propose to apply semantic similarity methods to tasks in Information Retrieval, Automatic Speech Recognition, and Computer Assisted Language Learning. We focus on multiple languages and on cross-language techniques. Information Retrieval from spoken documents can take advantage of a standard text-based IR system if a speech recognition system converts speech into written text. Speech recognizers, however, introduce a high error rate. We propose to correct automatic transcripts using semantic similarity methods. We also investigate techniques of improving the overall retrieval efficiency from spoken documents in a multilingual setting. Existing Computer-Assisted Language Learning tools do not give a student enough feedback to allow them to increase the learning rate. We propose extensions of such tools that include automatically-produced exercises with false friends and cognate words. Cognates are words that have similar spellings and meanings in different languages. They can help a second-language learner in the tasks of vocabulary expansion and reading comprehension. The learner also needs to pay attention to false friends: pairs of words that appear similar but have in fact different meanings in some or all contexts. Another automated tool that we propose is a semantic corrector that assists a second-language writer by detecting wrong usage of words in context.
Program
Discovery Grants Program - Individual
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
298150-2007
Name nom
Inkpen, Diana
Department département
Information Technology and Engineering, School of
Organization id
28
Institution établissement
University of Ottawa
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2009
Competition year année de concours
2007
Award amount
17000
Program id
RGPIN
Program nane 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
802
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information systems and technology
Area of application fr
Systèmes d'information et technologie de l'information
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
3
Nb partie
5
Application title
Natural language processing for speech information retrieval and computer-assisted language learning
Keyword
NA
Application summary
Existing search engines allow a user to retrieve useful information from texts on the Internet, but not from audio documents such as broadcast news or other recordings. The user has to browse through long audio recordings to find relevant parts. Despite much progress both in commercial applications and in research prototypes that deal with natural language, their performance of information retrieval systems still needs to be improved. We propose new ways of combining symbolic and statistical methods for dealing with the meaning of words and sentences. We plan to apply them in several tasks where they have not yet been tried. In particular, we propose to apply semantic similarity methods to tasks in Information Retrieval, Automatic Speech Recognition, and Computer Assisted Language Learning. We focus on multiple languages and on cross-language techniques. Information Retrieval from spoken documents can take advantage of a standard text-based IR system if a speech recognition system converts speech into written text. Speech recognizers, however, introduce a high error rate. We propose to correct automatic transcripts using semantic similarity methods. We also investigate techniques of improving the overall retrieval efficiency from spoken documents in a multilingual setting. Existing Computer-Assisted Language Learning tools do not give a student enough feedback to allow them to increase the learning rate. We propose extensions of such tools that include automatically-produced exercises with false friends and cognate words. Cognates are words that have similar spellings and meanings in different languages. They can help a second-language learner in the tasks of vocabulary expansion and reading comprehension. The learner also needs to pay attention to false friends: pairs of words that appear similar but have in fact different meanings in some or all contexts. Another automated tool that we propose is a semantic corrector that assists a second-language writer by detecting wrong usage of words in context.