Plan Course requirements Motivation Resources for Computational - - PowerPoint PPT Presentation

▶
plan
SMART_READER_LITE
LIVE PREVIEW

Plan Course requirements Motivation Resources for Computational - - PowerPoint PPT Presentation

Nov 01, 2022 474 likes •536 views

Plan Course requirements Motivation Resources for Computational Linguists Course plan WS 05/06 Topic assignments Intro Ivana Kruijff-Korbayov Magdalena Wolska 24 October 2005 WS05/06 Resources for CompLingsts

slide-1
SLIDE 1

Resources for Computational Linguists WS 05/06 Intro

Ivana Kruijff-Korbayová Magdalena Wolska

24 October 2005 WS05/06 – Resources for CompLing’sts – Introduction 2/15

Plan

  • Course requirements
  • Motivation
  • Course plan
  • Topic assignments

24 October 2005 WS05/06 – Resources for CompLing’sts – Introduction 3/15

Course requirements

24 October 2005 WS05/06 – Resources for CompLing’sts – Introduction 4/15

Motivation

  • plenty of NLP resources available

– what kinds? – what they do? – how can be used?

  • survey of available resources
  • by end of the course: be aware of what’s „out-there”

(know the notions, keywords, have seen some outputs, have heard of tasks in which used, etc.)

slide-2
SLIDE 2

24 October 2005 WS05/06 – Resources for CompLing’sts – Introduction 5/15

Motivation

examples of NLP applications

– user interfaces (e.g. voice-operated robots) – question answering (www.ask.com) – information retrieval – dialog systems (e.g. DB, ATT customer service) – summarization – text seneration (e.g. automatic reporting from data, proof verbalization)

24 October 2005 WS05/06 – Resources for CompLing’sts – Introduction 6/15

Motivation

typical pipeline

speech/text in speech/text out

NLP

24 October 2005 WS05/06 – Resources for CompLing’sts – Introduction 7/15

Motivation

typical pipeline

speech/text in speech/text out

NLP

some sub-components of every NLP module are „standard” certain methods and tools are „standard” tools and resources can be and are re-used

  • r are used to create other resources

24 October 2005 WS05/06 – Resources for CompLing’sts – Introduction 8/15

Motivation

typical pipeline

– pre-process input – shallow process and/or deep process

  • extract linguistic information
  • add information
  • infer information

– decide on contextually meaningful output

speech/text in speech/text out

NLP

slide-3
SLIDE 3

24 October 2005 WS05/06 – Resources for CompLing’sts – Introduction 9/15

Motivation

typical pipeline

speech/text in speech/text out

NLP

a n a l y z e c o r p o r a

– pre-process input – shallow process and/or deep process

  • extract linguistic information
  • add information
  • infer information

– decide on contextually meaningful output

24 October 2005 WS05/06 – Resources for CompLing’sts – Introduction 10/15

Motivation

typical pipeline

speech/text in speech/text out

NLP

a n a l y z e c o r p o r a

– pre-process input – shallow process and/or deep process

  • extract linguistic information
  • add information
  • infer information

– decide on contextually meaningful output

tokenization

24 October 2005 WS05/06 – Resources for CompLing’sts – Introduction 11/15

Motivation

typical pipeline

speech/text in speech/text out

NLP

a n a l y z e c o r p o r a

– pre-process input – shallow process and/or deep process

  • extract linguistic information
  • add information
  • infer information

– decide on contextually meaningful output

tokenization tagging, chunking, syntactic, semantic parsing, lexical analysis, domain-specific reasoning

24 October 2005 WS05/06 – Resources for CompLing’sts – Introduction 12/15

Motivation

typical pipeline

speech/text in speech/text out

NLP

a n a l y z e c o r p o r a

– pre-process input – shallow process and/or deep process

  • extract linguistic information
  • add information
  • infer information

– decide on contextually meaningful output

tokenization tagging, chunking, syntactic, semantic parsing, lexical analysis, domain-specific reasoning planning

slide-4
SLIDE 4

24 October 2005 WS05/06 – Resources for CompLing’sts – Introduction 13/15

Motivation

typical pipeline

speech/text in speech/text out

NLP

a n a l y z e c o r p o r a

– pre-process input – shallow process and/or deep process

  • extract linguistic information
  • add information
  • infer information

– decide on contextually meaningful output

tokenization tagging, chunking, syntactic, semantic parsing, lexical analysis, domain-specific reasoning planning l e a r n f r

  • m

c

  • r

p

  • r

a

24 October 2005 WS05/06 – Resources for CompLing’sts – Introduction 14/15

Course outline

24 October 2005 WS05/06 – Resources for CompLing’sts – Introduction 15/15

Topic assignments

24 October 2005 WS05/06 – Resources for CompLing’sts – Introduction 16/15

Motivation

typical pipeline

speech/text in speech/text out

NLP

a n a l y z e c o r p o r a

– pre-process input – shallow process and/or deep process

  • extract linguistic information
  • add information
  • infer information

– decide on contextually meaningful output

tokenization tagging, chunking, syntactic, semantic parsing, lexical analysis, domain-specific reasoning planning l e a r n f r

  • m

c

  • r

p

  • r

a

slide-5
SLIDE 5

24 October 2005 WS05/06 – Resources for CompLing’sts – Introduction 17/15

Motivation

typical pipeline

speech/text in speech/text out

NLP

a n a l y z e c o r p o r a

– pre-process input – shallow process and/or deep process

  • extract linguistic information
  • add information
  • infer information

– decide on contextually meaningful output

tokenization tagging, chunking, syntactic, semantic parsing, lexical analysis, domain-specific reasoning planning l e a r n f r

  • m

c

  • r

p

  • r

a