Pertemuan 21 Natural Language Processing Introduction Matakuliah

advertisement
Matakuliah
Tahun
Versi
: T0264/Intelijensia Semu
: Juli 2006
: 2/1
Pertemuan 21
Natural Language Processing
Introduction
1
Learning Outcomes
Pada akhir pertemuan ini, diharapkan mahasiswa
akan mampu :
• << TIK-99 >>
• << TIK-99>>
2
Outline Materi
•
•
•
•
•
Materi 1
Materi 2
Materi 3
Materi 4
Materi 5
3
Language Processing Problem
• Processing written text, using lexical,
syntactic, and semantic knowledge of the
language as well as the required real
world information.
• Processing spoken language, using all the
information needed above plus additional
knowledge about phonology as well as
enough added information to handle the
further ambiguities that arise in speech.
4
Features of Language That Make It Both
Difficult and Useful
The Problem : English sentences are incomplete
descriptions of the information that they are intended to
convey :
Some dogs are outside.
Some dogs are on the lawn.
Three dogs are on the lawn.
Rover, Tripp, and Spot are on the lawn.
The Good Side :
Language allows speakers to be as vague or as precise as
they like. It also allows speakers to leave out things they
believe their hearers already know.
5
Features of Language That Make It Both
Difficult and Useful contd’
The Problem: The same expression means
different things in different contexts:
Where’s the water ?
- in a chemistry lab, it must be pure
- when you are thirsty, it must be potable
- dealing with a leaky roof, it can be filthy
The Good Side : Language lets us communicate
about an infinite world using a finite (and thus
learnable) number of symbols.
6
Features of Language That Make It Both
Difficult and Useful contd’
The Problem: No natural language program can
be complete because new words, expressions,
and meanings can be generated quite freely:
I’ll fax it to you.
The Good Side : Language can evolve as the
experiences that we want to communicate about
evolve.
7
Features of Language That Make It Both
Difficult and Useful contd’
The Problem: There are lots of ways to say the
same thing :
Mary was born on October 11.
Mary’s birthday is October 11.
The Good Side : When you know a lot, facts imply
each other. Language is intended to be used by
agents who know a lot.
8
15.1. Introduction
• Understanding sudah membahas tentang type
language.
• Mangalami kesulitan dalam hal pemahaman
terhadap bahasa itu sendiri.
Oleh karena itu :
• Pengkajian bahasa melalui Natural Language
Processing (NLP).
• Dengan melakukan analisa morfologi, analisa
Sintaktis, analasi semantis, analisa integrasi dan
analisa pramatis.
9
15.1.1. Steps in the Process
• Morphological Analysis
Analisa kata tunggal atas komponen penyusunnya
• Syntactic Analysis
Analisa kata–kata yang beurutan untuk
mengatahui hubunganya dengan kata lainya.
“Boy the go the to store”
• Semantic Analysis
Menciptakan struktur baru berdasarkan hasil
analisa sintaktis untuk mengetahui arti dari kalimat
yang tersusun.
10
Introduction
• Discourse Integration
Menganalisa arti/makna dari kalimat tunggal untuk
mengetahui ketergantungan dan pengaruhnya
terhadap kalimat berikutnya.
- kata it dalam kalimat “John wanted it”
- mungkin kata John mempengaruhi kalimat berikutnya.
• Pragmatic Analysis
Menganalisa representasi struktur kalimat baru
untuk mengetahui apakah maknanya sesuai
dengan makna kalimat yang dimaksudkan.
“Do you know what time it is ?”  menanyakan waktu .
11
Morphological Analysis must do the following
“I want to print Bill’s.init file”.
• Kata Bill’s pada proper noun Bill dan akhiran ‘s
yang mengartikan kepemilikan.
• Mengenal .init sebagai ekstensi yang bermakna
adjective dalam kalimat tersebut.
• ‘s dalam kata prints berarti adanya plural atau
sebagai petunjuk third person singular verb (misal
dalam “he prints”.
• There will be ambiguity “want”, “print”, dan
“file”karena lebih dari satu kategori sintaktik.
12
The result of syntactic of :
“ I want print Bill’s .init file “
13
Semantic analysis must do :
• It must map individual word into
appropriate objects in the knowledge base
or database.
• It must create the correct structures to
correspond to the way the meaning of the
individual words combine with each other.
14
Partial meaning for a sentence
15
The result of Pragmatic Analysis of
“I want to print Bill’s .init file.”
Meaning
instance : Commanding
agent : User068
performer : This-System
Object : P27
P27
instance : Printing
agent : This-System
object : F1
This lead to the final result: lpr /wsmith/stuff.init
16
<< Closing >>
End of Pertemuan 21
Good Luck
17
Download