Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

NLP and LIS

How does Natural Language Processing (NLP) connect to Library & Information Science & Technology (LIS&T)? Recorded knowledge is stored as text. Texts have problematic properties. NLP can address some of the problems.
by

V Rubin

on 1 December 2015

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of NLP and LIS

Verbal
Communications
Texts
Language Technologies
1. Too many
2. Too long
3. Often contradictory
4. Lack structure
5. Have language identity
6. Silent or static
1. Select
2. Shorten/digest
3. Reconcile
4. Structure
5. Translate
6. Communicate
Problematic Properties?
Solutions in Principle?
Why LIS? Why Libraries?
LIS & T
Connecting
Language Technologies and LIS

Victoria Rubin, FIMS, UWO: Fall 2014
Recorded
Knowledge
Why should MLIS students care?
Jobs!
21 century information spaces:

"ubiquitously connected
and pervasively proximate “
UCaPP Mark Federman (2005)
Alternative careers within libraries or broader Information profession!
Out-of-the-box
thinking!
What do you need to be able to do?
=
use of computers
to represent & analyze human language,
or different kinds of information encoded in a free text form
aka Natural Language Processing
Types
1. IR, Question Answering
2. Automated Summarization &– Abstraction
3. Multi-Document Summaries
4. Layered analyses – rely on linguistic insights or probabilities
5. Machine Translation, Cross-Language IR
6. Text-to-Speech, Speech Recognition, Conversational Agents
Ls
- have a mandate of Knowledge Organization & Access
I
- is not restricted to Ls
S
- brings new methods
&T!
- not too be ignored as computing of the methods
Know (a bit) about
Find out student population by university? (e.g., GoogleSquares)
Sort images by mood?
Find lesson plans by grade?
Music downloads (e.g., Nokia) by country + time of day + genre: what does it tell you about the population preferences?
Delegate some tasks to
end-user needs
to be employed outside of libs
Be aware
of automated text solutions
Be prepared
"KNOW- HOW"
language
computers
Know your
http://www.goarmy.com/ask-sgt-star.html
to make sense of information
Full transcript