Grant: Discovery Grants Program - Individual
University of Guelph
$15,000.00
Disambiguation in natural language user interfaces of service robots
FY 2011-12
Summary
In the proposed research, we develop disambiguation techniques for building natural language user interfaces of service robots.
Service robots are used by ordinary people in their homes and offices, etc. They help people do house work, care seniors, conduct office duties, and so on. Most of the users of service robots are not specially trained personnel. For such users, a desirable way to control or communicate with service robots is through natural language interfaces. That is, users use instructions/commands in natural languages to control service robots. A core function of a natural language interface is to translate user natural language instructions into machine commands. So far, techniques for developing robot natural language interfaces are far from mature. A major challenge in building a robot natural language interface is handling ambiguity in natural language instructions. A natural language instruction may be ambiguous when it can be interpreted in different ways, and when it contains grammatical/lexical errors. Ambiguity may result in incorrect translation.
In this research, we develop a set of new techniques for disambiguation. In developing our techniques, we take into consideration the special features of robot applications, in addition to the general features of natural language user interfaces. In our techniques, knowledge about actions and behavior plays a key role in handling ambiguity. The techniques will help a robot natural language interface understand, in a knowledgeable way, natural language user instructions containing ambiguity. The technique can be used to build service robots that are more user-friendly and more accessible to ordinary people.
Program
Discovery Grants Program - Individual
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
105476-2010
Name nom
Wang, Fangju
Department département
Computing and Information Science, School of
Organization id
24
Institution établissement
University of Guelph
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2011
Competition year année de concours
2010
Award amount
15000
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
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
1206
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Engineering
Area of application fr
Génie
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
2
Nb partie
5
Application title
Disambiguation in natural language user interfaces of service robots
Keyword
NSERC
Application summary
In the proposed research, we develop disambiguation techniques for building natural language user interfaces of service robots.
Service robots are used by ordinary people in their homes and offices, etc. They help people do house work, care seniors, conduct office duties, and so on. Most of the users of service robots are not specially trained personnel. For such users, a desirable way to control or communicate with service robots is through natural language interfaces. That is, users use instructions/commands in natural languages to control service robots. A core function of a natural language interface is to translate user natural language instructions into machine commands. So far, techniques for developing robot natural language interfaces are far from mature. A major challenge in building a robot natural language interface is handling ambiguity in natural language instructions. A natural language instruction may be ambiguous when it can be interpreted in different ways, and when it contains grammatical/lexical errors. Ambiguity may result in incorrect translation.
In this research, we develop a set of new techniques for disambiguation. In developing our techniques, we take into consideration the special features of robot applications, in addition to the general features of natural language user interfaces. In our techniques, knowledge about actions and behavior plays a key role in handling ambiguity. The techniques will help a robot natural language interface understand, in a knowledgeable way, natural language user instructions containing ambiguity. The technique can be used to build service robots that are more user-friendly and more accessible to ordinary people.