Natural Language Processing - Class 1 - Introduction

Natural Language Processing - objectives of the course

• understand the various issues in NLP
• understand problems - ways to solve
• have tools to process text - lisp, unix, emacs

Grading

Computational Linguistics (CL)

• linguistics
• computer science
• cognitive sciences
• artificial intelligence (AI)

• formal theories about the linguistic knowledge that a human needs for generating and understanding language.
• formal models simulating aspects of the human language faculty and implement them as computer programmes.
• cognitive psychology - psycholinguisticsthat that examines the cognitive processes constituting human language use.

Applied CL

• practical outcome of modelling human language use.
• The methods, techniques, tools and applications in this area are often subsumed under the term language engineering or (human) language technology. Although existing CL systems are far from achieving human ability, they have numerous possible applications. The goal is to create software products that have some knowledge of human language improving human-machine interaction, using atural language interfaces, applications of such interfaces are database queries, information retrieval from texts, expert systems, robot control, machine translation, internet searchs, multimedia - language is the key for searching, filtering, routing, classification, summarization, automatic generation of reports

NLP is usualy divided into two main research fields:

Natural language understanding (NLU) : grammars use for understanding (not only to use if a clause is in the grammar or not), ambiguity of nl, context...

Natural language generation (NLG) : what is needed in order to generate smth in natural language? what kind of representations...

How is the research in NLP is done:

Language: has structure
syntax - smth can be syntactically correct , no meaning
semantics - smth can have meaning, but the intention is different.
pragmatics - sayings in context - definiteness, pronouns..
Levels of dealing in language:

• - syntax
• - morphology
• - phonetics
• - pragmatics
• - semantics

Examples

Word order change meaning: (example are from http://www.cs.columbia.edu/~kathy)

Which parts were damaged by larger machines?
Which parts damaged larger machines?
Which larger machines damaged parts?

Words has many meanings

John picked up a bad cold.
John picked up a large rock.
John picked up Radio Netherlands on his radio.

Context changes meaning

Scene 1:	Pennsylvania Station, NYC
	Bonnie: Long Beach? Passerby: Downstairs, LIRR Station.
Scene 2:	Ticket Counter, LIRR Station
	Bonnie: Long Beach? Clerk: $4.50.
Scene 3:	Information Booth, LIRR Station
	Bonnie: Long Beach? Clerk: 4:19, Track 17.
Scene 4:	On the train, vicinity of Forest Hills
	Bonnie: Long Beach? Clerk: Change at Jamaica.
Scene 5:	On the next train, vicinity of Lynbrook
	Bonnie: Long Beach? Conductor: Right after Island Park.

A general example:

• Do we have to understand an article in order to summarize it?
• Can we summarize an article in a language we don't understand?
• What are the signs we use in an article in order to summarize it? (key words, strucutre, importrant parts)
• variety of methods: understand, statistical info only? (most common words.. ) or something in between (similar words..)
• do we need to understand and then to re-generate?
• What is a good summaraization? how can we evaluate it?

For any question, contact me: yaeln@cs.bgu.ac.il
Back to course homepage

Last modified February 21, 2000