Post on 01-Jun-2018
8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
1/49
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
Artificial Intelligence:
An easy introduction from a
computational linguistic perspective
Ciprian-Virgil Gerstenberger
Saami Language Technology, Giellatekno, University of Troms, Norway
24.11.2011 University of Murmansk
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
2/49
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
Outline
Artificial Intelligence (AI)
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
3/49
8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
4/49
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
Outline
Artificial Intelligence (AI)
Computational Linguistics (CL)
The TALK project
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
5/49
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
Outline
Artificial Intelligence (AI)
Computational Linguistics (CL)
The TALK project
Learning software project
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
6/49
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
What is Artificial Intelligence?
What is artificial?
all human made
What is intelligence?
the capacity to learn and solve problems(Webster dictionary)
the ability to think and act rationally
C C
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
7/49
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
Definitions
Artificial Intelligence is a branch of Science which deals with helpingmachines find solutions to complex problems in a more human-likefashion. This generally involves borrowing characteristics from humanintelligence, and applying them as algorithms in a computer friendlyway.
http://ai-depot.com/Intro.html
Artificial Intelligence (AI) is the area of computer science focusing oncreating machines that can engage on behaviors that humansconsider intelligent.
http://library.thinkquest.org/2705/
A tifi i l I t lli (AI) C t ti l Li i ti (CL) Th TALK j t L i ft j t
http://ai-depot.com/Intro.htmlhttp://library.thinkquest.org/2705/http://library.thinkquest.org/2705/http://ai-depot.com/Intro.htmlhttp://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
8/49
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
Measuring intelligence: Turing
The Turing Test (1950)
The computer is interrogated by a human via a teletype. It the
test passes if the human cannot tell if there is a computer or
human at the other end.
http://www.cs.cmu.edu/afs/cs/academic/class/15381-s07/www/slides/011607comboIntro.pdf
Is this test sufficient?
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://www.cs.cmu.edu/afs/cs/academic/class/15381-s07/www/slides/011607comboIntro.pdfhttp://www.cs.cmu.edu/afs/cs/academic/class/15381-s07/www/slides/011607comboIntro.pdfhttp://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
9/49
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
Measuring intelligence: Searle
The Chinese Room Argument John Searle (1980)
An English man knowing no Chinese locked in a room with Chinesesymbols(a data base)and a book of instruction for manipulating the
symbols(the program)would get Chinese symbols which, unknownto the person in the room, are questions in Chinese (the input). Byfollowing the instruction in the program the man is able to pass outChinese symbols which are correct answers to the questions (theoutput).
The program enables the person in the room to pass the TuringTest for understanding Chinese but he does not understand a word ofChinese.
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
10/49
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
Intelligent systems
http://www.cs.cmu.edu/afs/cs/academic/class/15381-s07/www/slides/011607comboIntro.pdf
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://www.cs.cmu.edu/afs/cs/academic/class/15381-s07/www/slides/011607comboIntro.pdfhttp://www.cs.cmu.edu/afs/cs/academic/class/15381-s07/www/slides/011607comboIntro.pdfhttp://find/http://goback/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
11/49
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
Intelligent systems
Key steps of a knowledge-based agent (Craik, 1943):
thestimulusmust be translated into an internalrepresentation
humans sensoric organs vs. machines sensors
therepresentationis manipulated by cognitive processesto derive new internal representations
humans representation? memory
these in turn are translated into action complex with humans sometimes unpredictable
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
12/49
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
Complexity and Efficiency
Solving problems
huge computational complexity
Does the intelligent system answer at all? space-time trade-offs
Does the intelligent systems answer in reasonable time?
optimizing the search by use of domain knowledge
heuristics pruning
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
13/49
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
Approaches to AI: Classification
Bottom-Up:
the machine will discover the world on its own,the way humans do
Top-Down: learning occurs from what is already known
What is the bottom?
observed data What is the top?
abstractions; data models
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/http://goback/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
14/49
g ( ) p g ( ) p j g p j
Basic tasks
Searching
filtering material of a certain type
Recognizing patterns
abstracting; classifying Constraint solving
satisfying a number of limitations
Reasoning (with uncertain information)
drawing conclusions; deduction; induction
Learning
world changing; maintaining an accurate model; dynamicity
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
15/49
g ( ) p g ( ) p j g p j
Approaches to AI: Examples
Pattern Recognition
Expert Systems
Human-Computer Interaction
Games
Auction design
Diagnosis
Neural Networks and Parallel Computation
Evolutionary Computation and Planning
Genetic Algorithms
Logic Programming
Robotics
http://find/http://goback/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
16/49
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
17/49
AI and Computational Linguistics
Computational Linguistics: central role within AI
Automatic Speech Recognition
one of the oldest pattern recognition tasks
Machine-Translation
ETAP-1 Russian English (starting in 1970s) Google services
Human-Machine Interaction
dialogue modeling dialogue systems
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
18/49
Definitions
Computational linguistics is the science of language with particularattention given to the processing complexity constraints dictated bythe human cognitive architecture. Like most sciences, computationallinguistics also has engineering applications.
http://www.cs.tcd.ie/courses/csll/CSLLcourse.html
Computational linguistics is the study of computer systems forunderstanding and generating natural language.
(Ralph Grishman, Computational Linguistics: An Introduction, Cambridge University Press 1986. )
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://www.cs.tcd.ie/courses/csll/CSLLcourse.htmlhttp://www.cs.tcd.ie/courses/csll/CSLLcourse.htmlhttp://find/http://goback/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
19/49
Natural Language Processing (NLP)
Spoken Language
Automatic Speech Recognition (ASR)
Speech Syntesis, e.g., Text-To-Speech (TTS)
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/http://goback/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
20/49
Natural Language Processing (NLP)
Written Language
Natural Language Analysis (NLA)
input utterance abstractions surface form meaning(s)
Natural Language Generation (NLG)
abstraction output utterance
meaning
surface form(s)
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
21/49
Approaches in CL
Rule-Based explicit encoding of linguistic knowledge
usually consisting of a set of hand-crafted, grammatical
rules
easy to test and debug require considerable human effort
often based on limited inspection of the data with an
emphasis on prototypical examples
often fail to reach sufficient domain coverage often lack sufficient robustness when input data are noisy
http://www.sfs.uni-tuebingen.de/~fr/teaching/ws05-06/icl/slides/lecture2.pdf
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://www.sfs.uni-tuebingen.de/~fr/teaching/ws05-06/icl/slides/lecture2.pdfhttp://www.sfs.uni-tuebingen.de/~fr/teaching/ws05-06/icl/slides/lecture2.pdfhttp://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
22/49
Approaches in CL
Data-Driven
implicit encoding of linguistic knowledge
often using statistical methods or machine learning
methods
require less human effort
require large-scale data sources
coverage directly proportional to the richness of the data
source
more adaptive to noisy data
http://www.sfs.uni-tuebingen.de/~fr/teaching/ws05-06/icl/slides/lecture2.pdf
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://www.sfs.uni-tuebingen.de/~fr/teaching/ws05-06/icl/slides/lecture2.pdfhttp://www.sfs.uni-tuebingen.de/~fr/teaching/ws05-06/icl/slides/lecture2.pdfhttp://find/http://goback/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
23/49
Application Areas
machine translation
speech recognition
speech synthesis
text generation
man-machine interfaces
intelligent word processing: spelling correction, grammar
correction
document management: information retrival, information
extraction, text summarization
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
24/49
The Project
Talk and Look: Tools for Ambient Linguistic Knowledge
funded by the EU as project No. IST-507802 within the 6th
Framework program
cooperation between
= German Research Center for Artificial Intelligency (DFKI)= University of Saarland, Germany (USAAR)= BOSCH= BMW
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
25/49
The Aims
focusing on the development of new technologies for
adaptive multimodal and multilingual human-computer
dialogue systems
make dialogue interfaces more conversational, robust,
intuitive, and user-adaptive
Long-term vision: users interacting naturally with devices and
services, in the home or car, using speech, graphics, or a
combination of the two
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
26/49
The SAMMIE Corpus
Collecting Data
multimodal MP3 player interaction experiment
car driving simulation and interaction with an MP3 player atthe same time
Wizard-of-Oz study
different humanwizardsdecide whether to ask a
clarification request in a multimodal manner or else to use
speech alone
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/http://goback/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
27/49
The Experiment
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/http://goback/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
28/49
The SAMMIE Corpus
Goals
learning policies form multimodal interaction based on
factors such as long vs. short song lists, interaction withthe mp3 player being not the main focus
learning multimodal presentation strategies
learning multimodal clarification strategies
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
29/49
The SAMMIE System
Developing a prototype of a dialogue system
to show natural, intuitive mixed-initiative interaction particular emphasis on multimodal turn-planning
particular emphasis on flexible natural language generation
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
30/49
The SAMMIE Multimodal System Architecture
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
31/49
System Architecture
Description
the classical approach of a pipelined architecture
multimodal fusion and fission modules as parts of the
dialogue manager
dialogue manager decides on the next system move,
based on its model of the tasks, the current context and
the result of the song database
generation of an appropriate message to the driver
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/http://goback/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
32/49
Interaction
A typical interaction with the SAMMIE system
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/http://goback/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
33/49
Multimodality
Screenshot of in-car final showcase systems GUI,main menu
push-to-talk (not barge-in!)
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
34/49
System integration: How?
Nuance java API for speech recognition
MySQL Database
Dialogue Manager
MARY Text-To-Speech java API for speech syntesis
. . .
Application Programming Interface (API)+
Middleware: The Open Agent Architecture (OAA)
OAA 2.x agent libraries for:
Prolog ANSI C/C++
Java
Compaqs Web Language
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
35/49
Example of integration
Generic MySQL query OAA agent
connect( host, port, user, pass, database, Result )
Tourist information scenario
retrieve all hotels which are cheaper than 30:
oaa Solve(sendGenericDBQuery( [id, name], [type=hotel,
price
8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
36/49
OAA Example
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://find/http://goback/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
37/49
The Oahpa! project
OAHPA!
a web-based, language learning program for North Saami
Computer-Assisted/Aided Language Learning (CALL)
http://oahpa.uit.no
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
http://oahpa.uit.no/http://oahpa.uit.no/http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
38/49
North Saami Oahpa!
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
S S O
http://find/http://goback/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
39/49
South Saami Oahpa!
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
Th L i U i
http://find/http://goback/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
40/49
The Learning Units
Simple learning units
Numra: exercise numerals
Leksa: train vocabulary
MorfaS: train word inflection
More complex learning units
MorfaC: train word inflection in context of a well-formed
sentence
Vasta: give answes to random questions
Sahka: interactive dialogues
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
Th I f t t
http://find/http://goback/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
41/49
The Infrastructure
General software
Django: a high-level Python Web framework for rapid
development of Web applications
MySQL database
Javascript for polishing up some web-features not
managable in Django only
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
Th I f t t
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
42/49
The Infrastructure
Special software
Xerox tools
= twolc: for morphophonology= lexc: for morphology
= xfst: for compiling transducer= lookup: for analysis and generation
Finite-State Morphology Finite-State Automata
VISLCG: parser for Constraint GrammarParsing Syntax Analysis
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
Th G
http://find/http://goback/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
43/49
The Games
Options
teaching book word class
dialectal form
level of difficulty
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
The Games
http://find/http://goback/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
44/49
The Games
Game Rating
for simple games, just match against the correct answers
from the database
for more complex games,expert knowledgestored in
different modules
= help information on request= XML-file for giving feedback on specific errors
= special parsers for dialogue moves for the dialogue unitSahkabased on Constraint Grammar
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
Rating vocabulary training
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
45/49
Rating vocabulary training
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
Rating dialogue answers
http://find/http://goback/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
46/49
Rating dialogue answers
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
Sahka
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
47/49
Sahka
Overview of the analysis process
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
Ideas
http://find/http://goback/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
48/49
Ideas
AI and CL for education projects usefull
reasoning: assumptions about the students knowledge on
a specific subject
specialized databases
language: special terminology; mixed of natural language
and special coding (mathematics, physics, chemistry, etc.)
specialized parsers
Think up your own project!
Artificial Intelligence (AI) Computational Linguistics (CL) The TALK project Learning software project
Conclusion
http://find/8/9/2019 ai-cl_introArtificial Intelligence: An easy introduction from a computational linguistic perspective
49/49
Conclusion
= intelligent program a matter of interpretation
= plenty of free software in the web to start your own project
you need an exact view on that it should be about= software integration via API and middleware
= specialised software for natural language input and output
your contribution
your knowledge of a specific domain
http://find/