2. What is Natural Language Processing?
• NLP is an interdisciplinary field that uses computational
methods to:
o Investigate the properties of written human language and
model the cognitive mechanisms underlying the
understanding and production of written language.
o Develop novel practical applications involving the
intelligent processing of written human language by
computer.
3. What is NLP? (cont.)
• NLP plays a big part in Machine learning techniques:
o automating the construction and adaptation of machine
dictionaries
o modeling human agents' desires and beliefs
essential component of NLP
closer to AI
• We will focus on two main types of NLP:
o Human-Computer Dialogue Systems
o Machine Translation
4. Human-Computer Dialogue Systems
• Usually with the computer modelling a human dialogue
participant
• Will be able:
o To converse in similar linguistic style
o Discuss the topic
o Hopefully teach
5. Current Capabilities of Dialogue Systems
• Simple voice communication with machines
o Personal computers
o Interactive answering machines
o Voice dialing of mobile telephones
o Vehicle systems
o Can access online as well as stored information
• Currently working to improve
6. The Future of H-C Dialogue Systems
• The final end result of human computer dialogue systems:
o Seamless spoken interaction between a computer and a human
• This would be a major component of making an AI that can pass
the Turing Test
• Be able to have a computer function as a teacher
7. Human Computer Dialogue in Fiction
• Halo's Cortana AI
o Made from models of a real human brain
o Made to run the ship
o Made very human conversations
• Ender's Game series: Jane
o Made from "philotic connection"
o Human conversation
8. Problems of Human-Computer Dialogue
• At the moment, most common computer dialogue systems (call
systems, chatter bots, etc.) cannot handle arbitrary input
o In many cases, the computer can only respond to "expected"
speech
o Call systems often compensate with "Sorry, I didn't get that,"
when something unexpected is said.
9. Problems of Human-Computer Dialogue
• Computers need to be able to learn and process colloquial speech
• Needed to understand informal speakers:
o Understanding varied responses for call systems
o Accounting for variations in spoken numbers
• Processing colloquialisms is also necessary for seamless dialogue,
where the computer must avoid sounding too formal
o John Connor: "No, no, no, no. You gotta listen to the way people
talk. You don't say 'affirmative,' or [stuff] like that. You say 'no
problemo.' "
10. Successes of Human-Computer Dialogue
• So far, human-computer dialogue has been most successful in
applications where information about a specific topic is sought
from the computer.
o Electronic calling systems: company-specific
o Travel agents: specific to an airline or destination
• However, more complex systems of human-computer dialogue
have been produced which can interpret more varied input.
o Physics tutoring system (ITSPOKE) which can analyze and
explain errors in the response to a physics problem.
o Allows for more complex input than "Yes," "No," or "Flight
UA-93"
• These still cannot compare to true human-human dialogue.
11. Machine Translation
• Important for:
o accessing information in a foreign language
o communication with speakers of other languages
• The majority of documents on the world wide web are in
languages other than English
12. Statistical Translation
• Rule based
• Works relatively well with large sets of data
• Used probability to translate text
• Natural translations
• Google
13. Example Based Translation
• Converts "parallel" lines of text between language
• Only accurate for simple lines
• Minimal pairs are easy
• Analogy based
14. Paraphrasing
• Takes words and makes them simpler automatically
• For example in Spanish conjugated words like usado may be
changed to usar
15. Future of Machine Translation
• Goal:
o Aim to be able to flawlessly translate languages
• Link Human-Computer Dialogue and Machine Translation
• Have someone be able to talk in one language to a computer,
translate for another person
• Translated Video Chat
16. Machine Translation in Fiction
• Star Wars: C-3P0
o Interpreter
o Could hear and translate alien languages
o Final goal of machine translation
• Star Trek: Universal Translator
o Computer can seamlessly translate alien languages
17. Problems
• Works well only with predictable texts.
• Doesn't work well with domains where people want
translation the most:
o spontaneous conversations
o in person
o on the telephone
o and on the Internet.
18. Problems
• Computers can't deal with ambiguity, syntactic irregularity,
multiple word meanings and the influence of context.
Time flies like an arrow.
Fruit flies like a banana.
• Accurate translation requires an understanding of the text,
situation, and a lot of facts about the world in general.
The box is in the pen.
19. Problems
• The sign is describing a
restaurant (the Chinese
text, 餐厅, means
"dining hall").
• In the process of making
the sign, the producers
tried to translate Chinese
text into English with a
machine translation
system, but the
software didn't work,
producing the error
message,
"Translation Server Error."
• The software's user didn't
know English and thought
the error message was the
translation.
20. Successes
• Product knowledge bases need to be translated into multiple
languages
• Hiring a large multilingual support staff is expensive
• Machine translation is cheaper and accurate with predictable
texts.
• Microsoft, Autodesk, Symantec, and Intel use it.
o Makes customers happy
o Still readable though slightly chunkier than human
translations