Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

Simon Fraser University

$20,000.00

Discourse parsing for summarization and sentiment detection

FY 2013-14

Summary
The proposed research bridges research in text structure and computational linguistics, with the goal of finding computational methods for text representation. I will investigate discourse parsing methods for different applications, such as summarization and sentiment detection. Discourse parsing is the classification of units in a text into a complete structure, usually a tree, with nodes labelled with the relation holding among the units. Texts have internal structure and are built hierarchically, through building blocks of different importance to the overall communicative intention behind the text. For example, a paragraph may consist of a claim and evidence supporting that claim. The claim is the most important part, and the evidence is secondary. I plan to develop computational methods for extracting this high-level structure in texts. These methods would be useful in applications such as sentiment detection and summarization. Sentiment is defined as subjective content, expressed in whether a text contains positive or negative views and opinions towards its subject matter (e.g., an opinion piece in a newspaper, a movie review, a report on a new product, an e-mail message, or a post on a bulletin board). In sentiment detection, extracting text structure would help us determine which are the most important parts of the text, so that we can extract sentiment from those only.This research will contribute to understanding and extracting information from text structure. One of the applications, sentiment detection and classification, constitutes a new method of searching and extracting information from large bodies of data (e.g., the Internet). It has applications in business intelligence, e-business, and detection of flames and spam. For instance, sentiment detection has been used to determine the sentiment of investors on public companies, based on postings to bulletin boards or chat rooms.
Program
Discovery Grants Program - Individual
Location
British Columbia, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
261104-2008
Name nom
Taboada, MaiteMariaTeresa
Department département
Linguistics
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
2013
Competition year année de concours
2008
Award amount
20000
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
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
5
Nb partie
5
Application title
Discourse parsing for summarization and sentiment detection
Keyword
NSERC
Application summary
The proposed research bridges research in text structure and computational linguistics, with the goal of finding computational methods for text representation. I will investigate discourse parsing methods for different applications, such as summarization and sentiment detection. Discourse parsing is the classification of units in a text into a complete structure, usually a tree, with nodes labelled with the relation holding among the units. Texts have internal structure and are built hierarchically, through building blocks of different importance to the overall communicative intention behind the text. For example, a paragraph may consist of a claim and evidence supporting that claim. The claim is the most important part, and the evidence is secondary. I plan to develop computational methods for extracting this high-level structure in texts. These methods would be useful in applications such as sentiment detection and summarization. Sentiment is defined as subjective content, expressed in whether a text contains positive or negative views and opinions towards its subject matter (e.g., an opinion piece in a newspaper, a movie review, a report on a new product, an e-mail message, or a post on a bulletin board). In sentiment detection, extracting text structure would help us determine which are the most important parts of the text, so that we can extract sentiment from those only.This research will contribute to understanding and extracting information from text structure. One of the applications, sentiment detection and classification, constitutes a new method of searching and extracting information from large bodies of data (e.g., the Internet). It has applications in business intelligence, e-business, and detection of flames and spam. For instance, sentiment detection has been used to determine the sentiment of investors on public companies, based on postings to bulletin boards or chat rooms.