1. Information Retrieval
Take a query and a set of documents.
Select the subset of documents (or parts of documents) that match the query
Statistical approaches
Look at things like word frequency
More knowledge based approaches interesting, but maybe not helpful

2. Information Extraction
From a set of documents, extract “interesting” pieces of data
Hand-built systems
Learning pieces of the system
Learning the entire task (for certain versions of the task)
Wrapper Induction

3. IE Demo

4. Question Answering
Given a question and a set of documents (possibly the web), find a small portion of text that answers the question.
Some work on putting answers together from multiple sources.

5. QA Demos

6. Text Mining Outgrowth of data mining.
Trying to find “interesting” new facts from texts.
One approach is to mine databases created using information extraction.

7. Pragmatics
Distinctions between pragmatics and semantics get blurred in practical systems
To be a practically useful system, some aspects of pragmatics must be dealt with, but we don’t often see people making a strong distinction between semantics and pragmatics these days.
Instead, we often distinguish between sentence processing and discourse processing

8. What Kinds of Discourse Processing Are There?
Anaphora Resolution
Pronouns
Definite noun phrases
Handling ellipsis
Topic
Discourse segmentation
Discourse tagging (understanding what conversational “moves” are made by each utterance)

9. Approaches to Discourse
Hand-built systems that work with semantic representations
Hand-built systems that work with text (or recognized speech) or parsed text
Learning systems that work with text (or recognized speech) or parsed text

10. Issues Agreement on representation Annotating corpora
How much do we use the modular model of processing?

11. Summarization
Short summaries of a single text or summaries of multiple texts.
Approaches:
Select sentences
Create new sentences (much harder)
Learning has been used some but not extensively

12. Machine Translation Best systems must use all levels of NLP
Semantics must deal with the overlapping senses of different languages
Both understanding and generation
Advantage in learning: bilingual corpora exist--but we often want some tagging of intermediate relationships
Additional issue: alignment of corpora

13. Approaches to MT Lots of hand-built systems Some learning used
Probably most use a fair bit of syntactic and semantic analysis
Some operate fairly directly between texts

14. Generation Producing a syntactically “good” sentence
Interesting issues are largely in choices
What vocabulary to use
What level of detail is appropriate
Determining how much information to include

15. Strong vs. Weak AI “Weak” AI “Strong” AI
Claims that the digital computer is a useful tool for studying intelligence and developing useful technology.
A running AI program is at most a simulation of a cognitive process but is not itself a cognitive process.
Analogously, a meteorological computer simulation of a hurricane is not a hurricane.
“Strong” AI
Claims that a digital computer can in principle be programmed to actually BE a mind, to be intelligent, to understand, perceive, have beliefs, and exhibit other cognitive states normally ascribed to human beings.

16. Ethical issues in AI
What are the benefits and risks in attempting to develop AI programs?

17. Can Machines Act Intelligently?
The Turing test

18. Argument from informality
Human behavior is far too complex to be captured by any simple set of rules, and computer can only follow sets of rules, so computer cannot generate behavior as intelligent as that of humans.

19. Issues Raised
Need for background knowledge to achieve good generalization from examples
Learning should be possible without a teacher.
Learning should be possible in the face of a multitude of features.
Intelligent agents should be able to look for relevant information.

20. Could machines ever really think?
The mind-body problem
Dualist
Monist or materialist

21. Problems with dualism
Are you willing to accept the existence of an immaterial soul?
Note that the concept of the brain as hardware and the mind as software is a dualist concept.

22. Problems with materialism
Free will.
Consciousness

23. Thought Experiments
Brain in a vat
Brain prosthesis
The Chinese room

24. Argument from disability
What is this?
What responses can we make?

25. Gödel's Incompleteness Theorem
Not necessarily applicable to computers, which aren’t really Turing machines.
Being able to establish mathematical truth may not be the same as acting intelligently.
Humans are inconsistent in their thinking.