Friday, April 6, 2012

Trickster folkloric characters and my evolving thesis idea

I read an excerpt that I find interesting especially as I consider folkloric characters such as Anansi, Sly Mongoose and Doctorbird as possible options for the AI conversational agent.

"Trickster has particular purposes within cultural stories as educator and teacher. The trickster typically teaches by making mistakes so listeners can hear the stories and learn from the mistakes so they do not have to make them themselves. Trickster typically has some human and some superhuman characteristics and possibly some animal characteristics as well that allow him to get into situations that otherwise would not be possible thus allowing stories to consider complex cultural, emotional, physical, mental, and spiritual domains." (Iseke-Barnes 2009)

Interesting ideas. I never saw it that way. I saw Anasi stories as teaching us the qualities of deception and deceiving other people which I felt ingrained corruption and 'conmanship' in the African diaspora.

My discovery that Native Canadians (or the Indigenous people of Canada) also have trickster stories also makes my thesis idea more relevant to not only Jamaica, but to Canada as well. Hopefully I can establish that AI conversational agents based on one's cultural stories may be effective in the online world in transferring knowledge and information, and in helping people make sense of their activities or world.



Reference:

Iseke-Barnes, J. (2009). Unsettling fictions: Disrupting popular discourses and trickster tales in books for children. Journal of the Canadian Association for Curriculum Studies,

Monday, April 2, 2012

Applying Linguistics to Library and Information Studies

By doing the course: Language technologies for Libraries and Beyond at my university got me interested in Linguistics and what it has to offer in libraries and information studies. I will basically summarise my thoughts based on what I have been exposed to in my course.

The area of applied linguistics and natural language computing is a relatively new area for library and information science (more so for information science than libraries). However there are a number of natural language processing applications that are useful to libraries including information extraction, automatic summarisation, computer assisted language learning, speech recognition, question answering systems and dialogue systems. So applied linguistics, and in particular, the computing of language is definitely an area that could be considered as an attractive course.

Applied linguistics could also be used in examining library service (reference query) transactions, plus studying problems of how language impedes or facilitates access to information. Development of ontologies is another area of relevance to libraries and to information science in particular.

Regarding my thesis idea, I Wanted to explore as my thesis the idea of using a Folkloric artificial intelligent conversational agent to provide business/government information to micro-enterprise owners. Still immature but I am trying to talk with potential advisers to help me refine it. The folkloric character - Anansi - and perhaps other Jamaican characters like Sly Mongoose, Doctorbird, Patoo Owl are some of the characters that I am considering using.

Regarding the artificial intelligent conversational agent, I am just using existing systems that attempt to simulate conversation with people, by pattern matching algorithms and extracting output responses from pre-populated databases of rules and responses.There are two systems that allow one to  freely develop a computer-based agent that simulates dialogue with human beings: http://site.mycybertwin.com/ and http://www.pandorabots.com/botmaster/en/~182d3afe91fba45b3cc71bda~/home.

I want to use such agents to provide information, perhaps providing a new way to access government documents through natural language query, that will reduce the hassle of interacting with unpleasant civil servants, using phone lines or waiting for response to emails. Not to mention the other issues with locating relevant documents or information within the documents.