Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

University of Alberta

$17,000.00

Natural Language Processing at the Sub-Word Level

EF 2014-15

Résumé
Processing language involves processing words. However, words are not indivisible abstract atoms -they are made of smaller units, such as morphemes, syllables, letters, and phonemes. In computationallinguistics, words are analyzed on distinct levels: phonetic, phonological, orthographic,morphological, etc. These levels of representation underlie such important tasks as morphologicalparsing, speech synthesis and recognition, spell-checking, and stemming. Since different levels arestrongly inter-related, the understanding of the interactions between them is crucial to advancing thestate of the art in word-oriented applications. My objective is to investigate such interactions, anddevelop algorithms for alignment and conversion between levels. In particular, I will focus on thetasks of grapheme-to-phoneme conversion and transliteration.My general approach to the problem will be to incorporate linguistic knowledge into advancedmachine-learning techniques, which, given sufficient training data, substantially outperformrule-based approaches. However, the latter often achieve impressive accuracy without any need fortraining data. They also tend to perform well across different domains. I will explore the ways ofcombining the two paradigms, by exploiting linguistic understanding for guiding and informing machinelearning approaches, as well as for pre- and post-processing their training data.The long term goals of this research programme are acquiring deeper understanding of the dependenciesbetween various representations, and leveraging the novel insights in order to advance the state ofthe art in natural language processing. I am confident that the implementation of the planned projectswill result in successful applications in other areas of natural language processing.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Alberta, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
261284-2012
Name nom
Kondrak, Grzegorz
Department département
Computing Science
Organization id
9
Institution établissement
University of Alberta
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2014
Competition year année de concours
2012
Award amount
17000
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
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
1207
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Information, computer and communication technologies
Area of application fr
Technologie de l'information, des ordinateurs et des réseaux de communications
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 at the Sub-Word Level
Keyword
NSERC
Application summary
Processing language involves processing words. However, words are not indivisible abstract atoms -they are made of smaller units, such as morphemes, syllables, letters, and phonemes. In computationallinguistics, words are analyzed on distinct levels: phonetic, phonological, orthographic,morphological, etc. These levels of representation underlie such important tasks as morphologicalparsing, speech synthesis and recognition, spell-checking, and stemming. Since different levels arestrongly inter-related, the understanding of the interactions between them is crucial to advancing thestate of the art in word-oriented applications. My objective is to investigate such interactions, anddevelop algorithms for alignment and conversion between levels. In particular, I will focus on thetasks of grapheme-to-phoneme conversion and transliteration.My general approach to the problem will be to incorporate linguistic knowledge into advancedmachine-learning techniques, which, given sufficient training data, substantially outperformrule-based approaches. However, the latter often achieve impressive accuracy without any need fortraining data. They also tend to perform well across different domains. I will explore the ways ofcombining the two paradigms, by exploiting linguistic understanding for guiding and informing machinelearning approaches, as well as for pre- and post-processing their training data.The long term goals of this research programme are acquiring deeper understanding of the dependenciesbetween various representations, and leveraging the novel insights in order to advance the state ofthe art in natural language processing. I am confident that the implementation of the planned projectswill result in successful applications in other areas of natural language processing.