Building a SemanticPrimitiveBased Lexical Consultation System

1
Building a Semantic-Primitive-Based Lexical
Consultation System

• prepared by Lim Beng Tat
• Supervisor Dr. Tang Enya Kong
• Dr. Guo Cheng Ming

2
Outline

• Introduction
• Objective
• Lexical Consultation system
• Example data Input and output.
• Overall design and tools.
• Applications

3
Introduction

• More than one billion documents on the Internet
  (Inktomi and the NEC Research Institute, 2000)
• Search Engine tends to return thousands of links
  for each search.
• Therefore, how to analyze and make use of
  information in documents?

4
Introduction (Cont)

• Online domain lexicons
• Computer - webopedia.com
• Chemistry - chemnet.com
• Astronomy, Chemistry, Mathematic and Physics -
  scienceworld.wolfram.com
• How to make use of these lexicons to analyze web
  documents within the same domain?

5
Introduction (Cont)

• However, most of lexicons are built for human
  use.
• Do not offer immediately usable resources
• E.g. Relationship between two word senses such as
  Hypernym/hyponym relation has not been explicitly
  defined.
• How can we construct lexicons which have
  information such as semantic and syntactic
  information explicitly defined for applications?

6
Objective

• Constructing domain lexicons which have
  information such as semantic and syntactic
  information explicitly defined for applications.
• Analyzing domain web documents using the newly
  constructed domain lexicons.

7
Lexical Consultation System (LCS)
Determining the relatedness or closeness among
word senses in a dictionary
Descriptive semantic primitives
8
Lexical Consultation System (LCS)
Pipillon project, FEM or Bilingual Knowledge
base
9
Tractable Bilingual Knowledge Bank (BKB)
1E
1M
1E
1M
(0-5,0-4)
(0-5,0-4)
kutip(1)v (3-4/3-4)
kutip(1)v (3-4/3-4)
kutip(2)v (3-4/3-4)
pick(1)v up(1)p (3-47-8/3-4)
pick(1)v up(1)p (3-47-8/3-4)
pick(1)v up(1)p (3-47-8/3-4)
(0-1,0-1)
(0-1,0-1)
(0-1,0-1)
(2-4,2-4)
(2-4,2-4)
dia(1)n (0-1/0-1)
(2-3,3-4)
he(1)n (0-1/0-1)
(2-3,3-4)
dia(1)n (0-1/0-1)
dia(1)n (0-1/0-1)
he(1)n
bola(1)n (2-3/2-4)
bola(1)n (2-3/2-4)
ball(1)n (3-4/2-4)
ball(1)n (3-4/2-4)
he(1)n (0-1/0-1)
he(1)n (0-1/0-1)
lelaki(3)n (0-1/0-3)
bola(1)n (2-3/2-4)
ball(1)n (3-4/2-4)
man(4)n (2-3/0-3)
0-1
0-1
itu(1)det (3-4/3-4)
itu(1)det (3-4/3-4)
the(2)det (2-3/2-3)
the(2)det (0-1/0-1)
old(3)adj (1-2/1-2)
the(1)det (2-3/2-3)
the(1)det (2-3/2-3)
itu (1)det (2-3/2-3)
tua (2)adj (1-2/1-2)
itu(1)det (3-4/3-4)
(0-1,0-1)
(0-1,0-1)
(0-1,0-1)
(3-4,2-3)
(3-4,2-3)
he pick the ball up 0-1 3-4 2-3 3-4
7-8
he pick the ball up 0-1 3-4 2-3 3-4
7-8
dia kutip bola itu 0-1 3-4 2-3 3-4
dia kutip bola itu 0-1 3-4 2-3 3-4
(2-3,3-4)
(2-3,3-4)
0the1old2man3pick4the5ball6up7
0lelaki1tua2itu3kutip4bola5itu6
10
The End

• Thank you.
• Any comments please send to btlim_at_cs.usm.my

11
LCS (Cont)
12
LCS (Cont)
Pipillon project, FEM or Bilingual Knowledge
base
13
Determining the relatedness or closeness among
word senses in a dictionary
Descriptive semantic primitives
14
Cookies do not act maliciously on
computer systems.They are merely text files
that can be deleted at any time they are not
plug ins nor are they programs. ..
Cookies do not act maliciously on
computer systems.They are merely text files
that can be deleted at any time they are not
plug ins nor are they programs. ..
Cookies, N, 1 do, V, 2 not, R, 4 act, V,
1 .. .. .. .. ..
15
(No Transcript)
16
(No Transcript)
17
Determining the relatedness or closeness among
word senses in a dictionary
Descriptive semantic primitives