|
Topic Name: Humorous ‘Robot'
Category: Robotics
Research persons: Julia Taylor & Dr. Lawrence J. Mazlack
Location: 811 C Rhodes Hall ,Cincinnati, Ohio, United States
Details
University of Cincinnati researchers Julia Taylor and Larry Mazlack recently
unveiled a "robot” — more accurately a software program — that recognizes
jokes. They reported the development at the American Association for Artificial
Intelligence conference in Vancouver, Canada. All bad jokes aside, their
research represents a step forward in computers reaching the capability of a
human mind.
There does not exist yet but American researchers already carried out an able
this software - to a certain extent - to detect the funs.
“That I lay? What do I lay?” “The last word which was useful to you was: I
lay.” “Terry towel! Perfect…” This small dialogue of Bobby Lapointe (the tube of
toilet) has what to make bugger a software of analysis of text. But the program
developped at the point at the university of Cincinnati by Julia Taylor and
Lawrence Mazlack, will arrive, him, to determine that it is about a fun.
Very serious, this work falls under a long series of research whose objective
is better to integrate the robots in the universe of the men. At the Laboratory
of artificial intelligence of MIT (Massachusetts Institute of Technology), for
example, Cynthia Breazeal and his team conceived celebrates it Kismet, reduced
to a head, able to express supposed emotions to facilitate the social relations
with the human ones. But it is necessary to go further and to include/understand
what the men tell. One would not only have, as in the song Sentimental torturer,
of same Bobby, a robot cuts out his Master who would have said to him “cut us”.
The task is immense… Less tedious robots?
The software of Julia Taylor and Lawrence Mazlack was initially nourished
with the vocabulary of a dictionary for children (in order to reduce the extent
of work for this prototype). Then the possible relations between all these words
were recorded in the data base. In front of a text, the software locates the
words which do not seem to have any relationship with the sentence. When it
finds one of them, it seeks the phonetically close words and, if there is one,
concludes that it is about a pun. It will not be made trap, for example, by
“fish-F” which will become again the catfish.
Taylor had the distinct task of “training” the computer by providing it with
information relative to American English at a child’s level. They developed an
extensive list of knock-knock jokes that turn on people’s names, particularly.
Knock, Knock
Who is there?
Dawn
Dawn who?
Dawn by the station, early in the morning
Knock, Knock
Who is there?
Wendy
Wendy who?
Wendy last time you took a bath?
Then they gave the “bot” several examples of words that can have different
meanings and homonyms, as in puns. The program then checks to see if the message
is consistent with what would make sense. If it doesn’t, the bot searches to see
if the word sounds similar to a word that would fit. If this is the case, the
bot flags it as humor.
Knock, Knock
Who is there?
Dismay
Dismay who?
Dismay not be a funny joke
“Even leaden puns are very difficult to understand as well,” says Taylor.
“With the knowledge that is in the ontology right now, there are very, very few
jokes (or puns) that the program can understand.”
“The ability to appreciate humor is an enormous increment in subtlety,” says
Professor Tom Mantei, a fellow researcher in UC’s College of Engineering. “You
need to know a lot to ‘get’ humor — a computer does not find it easy.”
"Part of the difficulty lies with the formality that computers and people
need to use to interact with each other," says Mazlack. "A critical aspect in
achieving sociable computing is being able to informally communicate in a human
language with computers. Computationally handling humor is critical to being
able to conduct an informal dialogue with a computer; Julia Taylor is making
good progress in advancing knowledge in this area — other people in my lab are
working on different aspects of less formal ways of using computers."
Knock, Knock
Who is there?
Police
Police who?
Police tell me some Knock Knock jokes
Here’s an example of one of the robot’s favorite jokes:
Mother to boy: “Johnny, you’ve been working in the garden a lot this summer.
Boy: “I know. My teacher told me to weed a lot.”
“Notice that the boy says the teacher told him to WEED. Since ‘weed’ sounds
similar to 'read,' the program can find this wordplay,” Taylor says.
Mantei adds, “This research is another step toward approaching the capability of
the human mind.”
Knock, Knock
Who is there?
Noah
Noah who?
Noah good place to find more jokes?
This software is thus for the moment only one detector of funs. According to the
magazine New Scientist, it a little disappointed the spectators who saw it with
work during a conference on the artificial intelligence, in Vancouver. Human
humor is made only funs… Besides the researchers regard their creation only as
one first stage, the following one consisting in analyzing the context to decide
if a sentence is funny or not.
But progress is already considerable and one can hope, if is not to inculcate
the direction of humor in the robots, at least to make them a little less
tedious when they are more numerous around us, the day when we will need small
beautiful torturers (as Bobby said).
About Researchers:
Dr. Lawrence J. Mazlack
Associate Professor
Computer Science Area
811 C Rhodes Hall
1-513-556-1883
ECECS Department
University of Cincinnati
Cincinnati, Ohio
mazlack@uc.edu
Continuing projects include:
Data mining
Natural Language understanding
Ontology development for the semantic web
Web search
Knowledge based systems.
Julia Taylor
tayloj8@email.uc.edu
In The Images- 1.Robot bobboy
2.Julia Taylor3.Dr. Lawrence J. Mazlack
| Related research: |
Active Flexible Cables for progress of the Robot’s ability to approach into Narrow Spaces: Tadokoro Laboratory, Bangladeshi graduate student is developing a humanoid robot, Can a Robot Get High School Students Interested in Studying Science and Engineering in College, Carnegie Mellon Building Robot for Lunar Prospecting, Internet-Controlled Robots : Built your own, MrBot : fully-actuated robot for image-guided access of the prostate gland., Neurosurgical Robotic Program to reach Cape Breton, Rescue Robot and Rescue System: Tadokoro Laboratory, Robot insects in the approach, Robot squeeze through holes with diameters much smaller than its normal width., Robots now as an assistant, Robots “hand-make” devices on nano assembly line, Spider-like Bot Walks on Water, Spot the robot: CS prof trains robotic dogs, The mobile surgical robot, Using a Laser Pointer Researchers Developed Robot that can Fetches Objects with Just a Point and a Click
|
|
