ch01 cs834

7/27/2019 ch01 cs834

1/19

An Introduction to Language Processing with Perl andProlog

Chapter 1: An Overview of Language Processing

Pierre Nugues

Lund University

[email protected]

http://www.cs.lth.se/home/Pierre_Nugues/

Pierre Nugues An Introduction to Language Processing with Perl and Prolog 1 / 19
http://localhost/var/www/apps/conversion/tmp/scratch_1/[email protected]://www.cs.lth.se/home/Pierre_Nugues/http://www.cs.lth.se/home/Pierre_Nugues/http://localhost/var/www/apps/conversion/tmp/scratch_1/[email protected]://find/http://goback/

7/27/2019 ch01 cs834

2/19


Applications of Language Processing

Spelling and grammatical checkers: MS Word

Text indexing and information retrieval on the Internet: Google,

Microsoft Bing, YahooTelephone information that understands some spoken questions: SJ(trains in Sweden) or Tellme.com in the United States

Speech dictation of letters or reports: IBM ViaVoice, Windows Vista

Translation: Google Translate, SYSTRAN

http://find/

7/27/2019 ch01 cs834

3/19

7/27/2019 ch01 cs834

4/19


Linguistics Layers

Sounds

Phonemes

Words and morphologySyntax and functions

Semantics

Dialogue


Ch 1 A O i f L P i
http://find/

7/27/2019 ch01 cs834

5/19


Sounds and Phonemes

Serious Cest par la It is that way


Ch t 1 A O i f L P i
http://goforward/http://find/http://goback/

7/27/2019 ch01 cs834

6/19


Lexicon and Parts of Speech

The big cat ate the gray mouse

The/article big/adjective cat/noun ate/verb the/article gray/adjective

mouse/nounLe/article gros/adjectif chat/nom mange/verbe la/article souris/nomgrise/adjectifDie/Artikel groe/Adjektiv Katze/Substantiv it/Verb die/Artikelgraue/Adjektiv Maus/Substantiv


http://find/

7/27/2019 ch01 cs834

7/19


Morphology

Word Root form

worked to work + verb + preterittravaille travailler + verb + past participlegearbeitet arbeiten + verb + past participle


http://find/

7/27/2019 ch01 cs834

8/19


Syntactic Tree

sentence

noun phrase verb phrase

article verb noun phrase

nounarticle

noun

The boy hit the ball


http://find/

7/27/2019 ch01 cs834

9/19


Syntax: A Classical View

A graph of dependencies and functions

The boy hit the ballSubject

ObjectVerb


http://find/

7/27/2019 ch01 cs834

10/19


Semantics

As opposed to syntax:

1 Colorless green ideas sleep furiously.

2 *Furiously sleep ideas green colorless.

Determining the logical form:

Sentence Logical representation

Frank is writing notes writing(Frank, notes).Francois ecrit des notes ecrit(Francois, notes).

Franz schreibt Notizen schreibt(Franz, Notizen).

http://find/

7/27/2019 ch01 cs834

11/19


7/27/2019 ch01 cs834

12/19

p g g g

Reference

Pierre wrote notes wrote(pierre, notes)

Pierre

Louis

Charlotte operating

systems

computational

linguistics

Prolog

programming

1. sentence 2. logical representation

3. real

world

referencing referencing


http://find/http://goback/

7/27/2019 ch01 cs834

13/19

g g g

Ambiguity

Many analyses are ambiguous. It makes language processing difficult.Ambiguity occurs in any layer: speech recognition, part-of-speech tagging,parsing, etc.

Example of an ambiguous phonetic transcription:The boys eat the sandwichesThat may correspond to:The boy seat the sandwiches; the boy seat this and which is; the buoyseat the sand which is


http://find/

7/27/2019 ch01 cs834

14/19

Models and Tools

Linguistics has produced an impressive set of theories and modelsLanguage processing requires significant resources

Models and tools have matured. Resources are available.Tools involve notably finite-state automata, regular expressions, rewritingrules, logic, statistics and machine learning.


http://find/http://goback/

7/27/2019 ch01 cs834

15/19

The Carsim System: A Text-to-Scene Converter

Texts XML Templates 3D Animation

Vehicule B venantde ma gauche, je me trouve dans lecarrefour, a faiblevitesse environ 40

km/h, quand le vehicule B, percutemon vehicule, et merefuse la priorite adroite. Le premier

choc atteint mon ailearriere gauche,

// Static ObjectsSTATIC [ROADTREE]// Dynamic ObjectsDYNAMIC [VEHICLE [ID = vehicule b;

INITDIRECTION = east;

= =NLP engine Java 3D animation program


http://find/

7/27/2019 ch01 cs834

16/19

Dialogue: The Persona Project from Microsoft Research

A conversation with Peedy

Turn Utterance[Peedy is asleep on his perch]

User: Good morning, Peedy.[Peedy rouses]

Peedy: Good morning.User: Lets do a demo.

[Peedy stands up, smiles]Peedy: Your wish is my command, what would you like to hear?User: What have you got by Bonnie Raitt?

[Peedy waves in a stream of notes, and grabs one as they rushby.]Peedy: I have The Bonnie Raitt Collection from 1990.User: Pick something from thatPeedy: How about Angel from Montgomery?


http://find/

7/27/2019 ch01 cs834

17/19

Dialogue: The Persona Project from Microsoft Research

User: Sounds good.[Peedy drops note on pile]

Peedy: OK.User: Play some rock after that.

[Peedy scans the notes again, selects one]

Peedy: How about Fools in love?User: Who wrote that?[Peedy cups one wing to his ear]

Peedy: Huh?User: Who wrote that?

[Peedy looks up, scrunches his brow]Peedy: Joe JacksonUser: Fine.

[Drops note on pile]


http://find/

7/27/2019 ch01 cs834

18/19

Persona System Architecture

Source: http:

//research.microsoft.com/research/pubs/view.aspx?pubid=439Pierre Nugues An Introduction to Language Processing with Perl and Prolog 18 / 19

http://research.microsoft.com/research/pubs/view.aspx?pubid=439http://research.microsoft.com/research/pubs/view.aspx?pubid=439http://research.microsoft.com/research/pubs/view.aspx?pubid=439http://research.microsoft.com/research/pubs/view.aspx?pubid=439http://find/http://goback/

7/27/2019 ch01 cs834

19/19

Research Relevance

Large companies like Microsoft, Google, Yahoo, IBM, or Xerox have a

research activity in natural language processing.The 7th European framework program (2007-2013) names six technologypillars in information technologies. Two of them are related to languageprocessing:

Knowledge, cognitive and learning systems: semantic systems;capturing and exploiting knowledge embedded in web and multimediacontent; bio-inspired artificial systems that perceive, understand, learnand evolve, and act autonomously; learning by convivial machines andhumans based on a better understanding of human cognition.

Simulation, visualization, interaction and mixed realities: tools forinnovative design and creativity in products, services and digitalmedia, and for natural, language-enabled and context-rich interactionand communication.

http://find/

ch01 cs834

Documents

Transcript of ch01 cs834