Morphosemantic Relations in and Across Wordnets:

1
Morphosemantic Relations in and Across
Wordnets A Study Based on Turkish
Orhan Bilgin, Özlem Çetinoglu, Kemal
Oflazer Sabanci University Human Languages and
Speech Technologies Laboratory Istanbul,
Turkey orhanb,ozlemc,oflazer_at_sabanciuniv.edu
2
OBJECTIVES

• Using morphological processes in Language A, we
  can
• extract explicit semantic relations in Language A
  and use these to enrich Wordnet A
• automatically prepare machine-tractable synset
  glosses for Wordnet A and/or B and most
  importantly
• discover implicit semantic relations in Wordnet B
  and use these to enrich Wordnet B.

3

• METHODOLOGY
• 1) Determine derivational affixes in Language A
• Rule of Thumb
• Prefer productive affixes with predictable
  semantics

4
METHODOLOGY
The chaotic agentive suffix -ci
-ci
5
METHODOLOGY
A more well-behaved suffix - li
-li
6
METHODOLOGY
2) Define the semantic effects of the affixes
7
METHODOLOGY
2) Extract morphosemantically-related pairs
boulder builder deer dresser father founder her ki
ller laser maker mother never teacher
boulder builder deer dresser father founder her ki
ller laser maker mother never teacher
MORPHOLOGICAL ANALYZER
CANDIDATES
WINNERS
ROOT (v) AGENT ?
8
METHODOLOGY
2) Extract morphosemantically-related pairs
build - builder dress - dresser found -
founder kill - killer make - maker teach - teacher
9
METHODOLOGY
3) Link pair members to ILI records
dress (v)
dresser (n)
?

• put on clothes
• dress in a certain manner
• dress with elaborate care
• put a dressing on
• convert into leather
• apply a bandage to
• give a neat appearance to
• arrange hair attractively
• put a finish on
• kill and prepare for consumption
• arrange in ranks
• provide with clothes
• cut back the growth of

• furniture for keeping clothes
• person who dresses in a particular way
• a wardrobe assistant for an actor
• a cabinet with shelves
• low table with mirror or mirrors

(1709-1784)
10
USES
1) Extract explicit semantic relations in the
language
taslasmak polimerlesmek iyonlasmak kemiklesmek bil
lurlasmak kireçlesmek plastiklesmek izomerlesmek k
eratinlesmek
taslastirmak polimerlestirmek iyonlastirmak kemikl
estirmek billurlastirmak kireçlestirmek plastikles
tirmek izomerlestirmek keratinlestirmek
tas polimer iyon kemik billur kireç plastik izomer
keratin
IS_CAUSED_BY
BECOME
11
USES
2) Share relations with other wordnets a) Pairs
in importing language are morphologically related
STATE_OF
deli
delilik
EXPORTING LANGUAGE
INTERLINGUAL INDEX
02005975-a
13580347-n
madness
mad
IMPORTING LANGUAGE
12
USES
2) Share relations with other wordnets a) Pairs
in importing language are morphologically related
STATE_OF
deli
delilik
EXPORTING LANGUAGE
INTERLINGUAL INDEX
02005975-a
13580347-n
madness
mad
IMPORTING LANGUAGE
STATE_OF
13
USES
2) Share relations with other wordnets b) Pairs
in importing language are morphologically
unrelated
CAUSES
yikmak
yikilmak
EXPORTING LANGUAGE
INTERLINGUAL INDEX
01931110-v
01614562-v
collapse
tear down
IMPORTING LANGUAGE
14
USES
2) Share relations with other wordnets b) Pairs
in importing language are morphologically
unrelated
CAUSES
yikmak
yikilmak
EXPORTING LANGUAGE
INTERLINGUAL INDEX
01931110-v
01614562-v
collapse
tear down
IMPORTING LANGUAGE
CAUSES
15
USES
3) Prepare simple synset glosses
WITH
omurga
omurgali
EXPORTING LANGUAGE
INTERLINGUAL INDEX
02422440-a
05268544-n
vertebrate
spine
IMPORTING LANGUAGE
16
USES
3) Prepare simple synset glosses
WITH
omurga
omurgali
EXPORTING LANGUAGE
INTERLINGUAL INDEX
02422440-a
05268544-n
vertebrate
spine
IMPORTING LANGUAGE
vertebrate with spine
17
USES
3) Prepare simple synset glosses
Some examples based on Turkish Wordnet
18
RESULTS
The current wordlist of Turkish contains a
substantial number of words derived from a small
set of suffixes.
19
RESULTS

• Detailed analysis of two suffixes
• Although Turkish Wordnet is a small-sized
  resource (10,000 synsets), it contains a
  significant number of synsets involving these two
  suffixes.
• In only a few cases does PWN indicate a CAUSES
  relation between the respective English synsets.
• In the case of the BECOME pairs, PWN provides the
  underspecified relation ENG_DERIVATIVE.