Class 1

NLP course:

• - general overview of NLP
• - ELIZA - pattern matching
• - parsers
• - generation:
  • planning
  • lexical choice
  • syntactic realization.
• assembling all parts together

NLP background:

- Computational Linguistics
- AI
Computational linguistics: linguistics theories, computational tools.

Aspects and target of research: - applicative - theoretical Developing nlp tools: compromising with theoretical terms.

• need for nlp research:
• machine translations
• human-computer interface.
• summarization
• information retrieval
• OCR, voice recognition
• 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

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?

This is never the final version of the page..
Back to the course home page