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.

Learning about Natural Language Processing and its applications for libraries, librarians and beyond

I attended my first Language and Computer technologies class today with Victoria Rubin. My professor opened my eyes for the first time to the fact that when libraries talk about library automation or library technologies, most of the time they exclude natural language processing technologies. She however raised the issue that this should not be the case, as there are lots of applications of computer processing natural language applicable to libraries.

For example:

• automated summarisation software to summarise a large document in a page or few paragrahs,
• machine translation applications to translate documents in foreign language
• automated indexing applications among many others.

Through her class, I caught her vision to extend library practice from beyond the technologies that libraries are already applying or talking about.

Rubin made the case that language can be processed by computers but that there are certain challenges that must be understood. Her main thesis was that computers can recognise and analyse human language, and with the right algorithms and understanding of the process in which human beings make sense of, interpret and use language, a lot of applications could be created that could further automate various library processes.

One such process is the reference service. Computers could be used to process user queries and reply to their questions, especially for those questions that require simple answers.

What she made clear was that once we can break up an intelligent human task into a sequence of steps, then algorithms could be written to enable computers to perform them.

Throughout the rest of this course, I will be learning about Natural Language Processing and its applications for libraries, librarians and beyond.

 As I sat in the class I thought about the myriad of ideas and work processes that I have in which I wanted automated. Grading and marking student papers is one. I want to be able to write or create an application that automatically marks a student's essay for me.

Also, I want to be able to take data that is not in any structure and use a software to structure that data for me so as to make it available for input into a database. Many times I get a list or directory in a text format, that I want to get into a database or spreadsheet format, and have to manually copy and paste to enter such data into the software application.

Then there is also my idea about cellular/mobile phone applications, where users can interact with a library's online catalogue through text or SMS messaging in order to retrieve data.

I am looking forward to learning about these new technologies that I have not seen in the library literature or heard being discussed at library conferences, except for those natural language processing applications that relate to assistive technologies.

Language Technologies and the Future of libraries: Preliminary thoughts

I was just looking at a course that I will be taking this semester entitled: “Language and Computer Technologies for Libraries and Beyond” .

The course introduced me to the IBM computer Watson that played Jeopardy and beat the best human champions. I also learned about Eliza, an intelligent agent (chatterbot) in the 1960's that tricked human beings into thinking that she was a real therapist who could help them talk about their problems.

It got me thinking that in the future, computers may be so intelligent, that we can design online systems that interact with people, without their knowledge that they are actually interacting with computers. These computers can then draw large datasets and analyse what information is required based on what the person is asking and deliver the right information to the user to meet the need expressed.

I see this applied in libraries in two ways:
1. virtual reference services
2. search of online catalogues

For virtual reference, instead of having a librarian, we can have an intelligent agent (or chatterbot) that can respond to the online user and guide the user based on what they ask to the right source online.

For the online catalogue search, we could design online systems that interprets what users put in the search box and retrieve the most relevant sources to the user query.

I already encounter these types of system through online systems that are designed to answer frequently asked questions. They have a database of questions and answers and are able to pull answers based on similarities between questions being asked to those that are already in their databases.