Transcript slides

The Relevance of a Cognitive
Model of the Mental Lexicon to
Automatic Word Sense
Disambiguation
Martha Palmer and Susan Brown
University of Colorado
August 23, 2008
HJCL /Coling, Manchester, UK
1
Outline


Sense Distinctions
Annotation

Sense Inventories created by human judgments






An hierarchical model of sense distinctions
OntoNotes


WordNet
PropBank and VerbNet
Mappings to VerbNet and FrameNet
Groupings
Empirical evidence of replicable sense distinctions
Reading response experiments based on the
hierarchical model
CLEAR – Colorado
HJCL2008
2
Word sense in Machine Translation

Different syntactic frames
John left the room
Juan saiu do quarto. (Portuguese)
 John left the book on the table.
Juan deizou o livro na mesa.


Same syntactic frame? Same sense?

John left a fortune.
Juan deixou uma fortuna.
CLEAR – Colorado
HJCL2008
3
Word sense in Machine Translation – not just
syntax

Different syntactic frames
John left the room
Juan saiu do quarto. (Portuguese)
 John left the book on the table.
Juan deizou o livro na mesa.


Same syntactic frame? Same sense?

John left a fortune to the SPCA.
Juan deixou uma fortuna.
CLEAR – Colorado
HJCL2008
HJCL2008--4
WordNet – Princeton
(Miller 1985, Fellbaum 1998)
On-line lexical reference (dictionary)
 Nouns, verbs, adjectives, and adverbs grouped into
synonym sets
 Other relations include hypernyms (ISA), antonyms,
meronyms
 Typical top nodes - 5 out of 25





(act, action, activity)
(animal, fauna)
(artifact)
(attribute, property)
(body, corpus)
CLEAR – Colorado
HJCL2008
5
WordNet – Princeton – leave, n.4, v.14
(Miller 1985, Fellbaum 1998)

Limitations as a computational lexicon





Contains little syntactic information
No explicit lists of participants
Sense distinctions very fine-grained,
Definitions often vague
Causes problems with creating training data for
supervised Machine Learning – SENSEVAL2



Verbs > 16 senses (including call)
Inter-annotator Agreement ITA 71%,
Automatic Word Sense Disambiguation, WSD 64%
Dang & Palmer, SIGLEX02
CLEAR – Colorado
HJCL2008
6
PropBank – WSJ Penn Treebank
Palmer, Gildea, Kingsbury., CLJ 2005
have been expecting
Arg1
Arg0
Analysts
a GM-Jaguar
pact
Arg0
*T*-1
Analysts have been expecting a GM-Jaguar pact
that would give the U.S. car maker an eventual
30% stake in the British company.
that would give
Arg2
the US car
maker
Arg1
an eventual 30% stake in the
British company
expect(Analysts, GM-J pact)
give(GM-J pact, US car maker, 30% stake)
CLEAR – Colorado
HJCL2008
PropBank - Palmer
7
Lexical Resource - Frames Files: give
Roles:
Arg0: giver
Arg1: thing given
Arg2: entity given to
Example:
double object
The executives gave the chefs a standing ovation.
Arg0:
The executives
REL:
gave
Arg2:
the chefs
Arg1:
a standing ovation
CLEAR – Colorado
HJCL2008
PropBank - Palmer
8
Word Senses in PropBank

Orders to ignore word sense not feasible for 700+
verbs


Mary left the room
Mary left her daughter-in-law her pearls in her will
Frameset leave.01 "move away from":
Arg0: entity leaving
Arg1: place left
Frameset leave.02 "give":
Arg0: giver
Arg1: thing given
Arg2: beneficiary
How do these relate to traditional word senses in VerbNet and WordNet?
CLEAR – Colorado
HJCL2008
PropBank - Palmer
9
Limitations to PropBank as a Sense
Inventory



Sense distinctions are very coarse-grained –
only 700 verbs
High ITA, > 94%,
High WSD,> 90%
CLEAR – Colorado
HJCL2008
PropBank - Palmer 10
Limitations to Levin Classes as a Sense
Inventory
Dang, Kipper & Palmer, ACL98



Coverage of only half of the verbs (types) in
the Penn Treebank (1M words,WSJ)
Usually only one or two basic senses are
covered for each verb
Confusing sets of alternations
Different classes have almost identical
“syntactic signatures”
 or worse, contradictory signatures

CLEAR – Colorado
HJCL2008 VerbNet – Kipper, Dang, Palmer11
Intersective Levin Classes
Kipper, Dang & Palmer, IJCAI00, Coling00


More syntactically and semantically coherent
 sets of syntactic patterns
 explicit semantic components
 relations between senses
Multiple class memberships viewed as base classes
and regular sense extensions
VERBNET
CLEAR – Colorado
HJCL2008
12
VerbNet – Karin Kipper

Class entries:
Capture generalizations about verb behavior
 Organized hierarchically
 Members have common semantic elements,
semantic roles and syntactic frames


Verb entries:
Refer to a set of classes (different senses)
 each class member linked to WN synset(s) (not
all WN senses are covered)

CLEAR – Colorado
HJCL2008
VerbNet
13
14
HJCL2008
Mapping from PropBank to VerbNet
(similar mapping for PB-FrameNet)
Frameset id =
leave.02
Sense =
give
VerbNet class =
future-having 13.3
Arg0
Giver
Agent/Donor*
Arg1
Thing given Theme
Arg2
Benefactive Recipient
Baker, Fillmore, & Lowe, COLING/ACL-98
Fillmore & Baker, WordNetWKSHP, 2001
*FrameNet Label
CLEAR – Colorado
HJCL2008
VerbNet
15
Mapping from PB to VerbNet
verbs.colorado.edu/~semlink
CLEAR – Colorado
HJCL2008
VerbNet
16
Mapping PropBank/VerbNet
http://verbs.colorado.edu/~mpalmer/verbnet




Extended VerbNet now covers 80% of
PropBank tokens. Kipper, et. al., LREC-04, LREC-06
(added Korhonen and Briscoe classes)
Semi-automatic mapping of PropBank
instances to VerbNet classes and thematic
roles, hand-corrected.
VerbNet class tagging as automatic WSD
Run SRL, map Arg2 to VerbNet roles, Brown
performance improves Yi, Loper, Palmer, NAACL07
CLEAR – Colorado
HJCL2008
VerbNet
17
Limitations to VN/FN as sense
inventories

Concrete criteria for sense distinctions






Distinct semantic roles
Distinct frames
Distinct entailments
But….
Limited coverage of lemmas
For each lemma, limited coverage of senses
CLEAR – Colorado
HJCL2008
18
Sense inventory desiderata


Coverage of WordNet
Sense distinctions captured by concrete
differences in underlying representations as
in VerbNet and FrameNet





Distinct semantic roles
Distinct frames
Distinct entailments
Start with WordNet and be more explicit
Groupings
CLEAR – Colorado
HJCL2008
19
WordNet: - leave, 14 senses, grouped
WN1, WN5,WN8
Depart, a job, a room, a
dock, a country
WN6 WN10 WN2 WN 4 WN9 WN11 WN12
WN14 Wnleave_off2,3 WNleave_behind1,2,3
Leave behind, leave alone
WNleave_alone1 WN13
Create a WN3
State WN7
WNleave_out1, Wnleave_out2
WNleave_off1
“leave off” stop, terminate
exclude
CLEAR – Colorado
HJCL2008
Groupings
20
WordNet: - leave, 14 senses, groups, PB
WN1, WN5,WN8
4
Depart, a job, a room, a
dock, a country (for X)
1
2
WN6 WN10 WN2 WN 4 WN9 WN11 WN12
WN14 WNleave_off2,3 WNleave_behind1,2,3
Leave behind, leave alone
WNleave_alone1 WN13
5
WN7an effect:
Create a WN3
State /cause
Left us speechless, leave a stain
WNleave_out1, WNleave_out2
exclude
CLEAR – Colorado
3
HJCL2008
WNleave_off1
stop, terminate:
the road leaves off, not
leave off your jacket, the results
Groupings
21
Overlap between Groups and
PropBank Framesets – 95%
Frameset2
Frameset1
WN1 WN2
WN3 WN4
WN6 WN7 WN8
WN5 WN 9 WN10
WN11 WN12 WN13
WN19
WN 14
WN20
develop
Palmer, Dang & Fellbaum, NLE 2007
CLEAR – Colorado
HJCL2008
Groupings
22
Sense Hierarchy
(Palmer, et al, SNLU04 - NAACL04, NLE07, Chen, et. al, NAACL06)

PropBank Framesets – ITA >90%
coarse grained distinctions
20 Senseval2 verbs w/ > 1 Frameset
Maxent WSD system, 73.5% baseline, 90%

Sense Groups (Senseval-2) - ITA 82%
Intermediate level
(includes Levin classes) – 71.7%

WordNet – ITA 73%
fine grained distinctions, 64%
CLEAR – Colorado
Tagging w/groups,
ITA 90%, 200@hr,
Taggers - 86.9%
Semeval07
Chen, Dligach & Palmer, ICSC 2007
HJCL2008
Groupings
23
Groupings Methodology – Human Judges
(w/ Dang and Fellbaum)


Double blind groupings, adjudication
Syntactic Criteria (VerbNet was useful)

Distinct subcategorization frames



call him a bastard
call him a taxi
Recognizable alternations – regular sense
extensions:



play an instrument
play a song
play a melody on an instrument
CLEAR – Colorado
HJCL2008
SIGLEX01, SIGLEX02, JNLE07
Groupings
24
Groupings Methodology (cont.)

Semantic Criteria

Differences in semantic classes of arguments


Differences in the number and type of arguments




Change of prior entity or creation of a new entity?
Differences in types of events


Often reflected in subcategorization frames
John left the room.
I left my pearls to my daughter-in-law in my will.
Differences in entailments


Abstract/concrete, human/animal, animate/inanimate, different
instrument types,…
Abstract/concrete/mental/emotional/….
Specialized subject domains
CLEAR – Colorado
HJCL2008
Groupings
25
Creation of coarse-grained resources

Unsupervised clustering using rules (Mihalcea &
Moldovan, 2001)



Clustering by mapping WN senses to OED
(Navigli, 2006).
OntoNotes - Manually grouping WN senses
and annotating a corpus (Hovy et al., 2006)
Supervised clustering WN senses using
OntoNotes and another set of manually
tagged data (Snow et al., 2007) .
CLEAR – Colorado
HJCL2008
Groupings
26
OntoNotes Goal: Modeling Shallow
Semantics DARPA-GALE



AGILE Team: BBN, Colorado, ISI,
Penn
Skeletal representation of literal
meaning
Synergistic combination of: Text




Syntactic structure
Propositional structure
Word Sense
Word sense
wrt Ontology
Coreference
CLEAR – Colorado
HJCL2008
Treebank
PropBank
OntoNotes
Annotated Text
Co-reference
27
Empirical Validation – Human Judges
the 90% solution (1700 verbs)
Leave 49% -> 86%
CLEAR – Colorado
HJCL2008
Groupings
28
Question remains: Is this the “right” level
of granularity?



“[Research] has not directly addressed the
problem of identifying senses that are distinct
enough to warrant, in psychological terms, a
separate representation in the mental
lexicon.” (Ide and Wilks, 2006)
Can we determine what type of distinctions
are represented in people’s minds?
Will this help us in deciding on sense
distinctions for WSD?
CLEAR – Colorado
HJCL2008
29
Sense Hierarchy

PropBank Framesets – ITA >90%
coarse grained distinctions
20 Senseval2 verbs w/ > 1 Frameset
Maxent WSD system, 73.5% baseline, 90%

Sense Groups (Senseval-2) - ITA 82%
Intermediate level
(includes Levin classes) – 71.7%

WordNet – ITA 73%
fine grained distinctions, 64%
CLEAR – Colorado
HJCL2008
Groupings
30
Computational model of the lexicon
based on annotation



Hypothesis: Syntactic structure overtly marks
very coarse-grained senses
Subsequently subdivided into more and more
fine-grained distinctions.
A measure of distance between the senses

The senses in a particular subdivision share
certain elements of meaning.
CLEAR – Colorado
HJCL2008
31
Psycholinguistic theories on semantic
representations – Susan Brown

Discrete-senses theory (Klein and Murphy, 2001)



Each sense has its own separate representation.
Related senses and unrelated senses are stored
and processed in the same way
Shared-representation theory (Rodd et al., 2002)

Related senses share a portion of their meaning
representation
CLEAR – Colorado
HJCL2008
Brown, ACL08
32
Hypotheses
Broke the
radio (WN 3)
Broke the
vase (WN 5)
DiscreteSenses
CLEAR – Colorado
HJCL2008
Brown, ACL08
33
Hypotheses
Broke the
radio (WN 3)
DiscreteSenses
CLEAR – Colorado
Broke the
vase (WN 5)
Slow access
HJCL2008
Brown, ACL08
34
Hypotheses
Broke the
radio (WN 3)
DiscreteSenses
CLEAR – Colorado
Broke the
vase (WN 5)
Broke the
horse (WN 12)
Slow access
HJCL2008
Brown, ACL08
35
Hypotheses
Broke the
radio (WN 3)
DiscreteSenses
CLEAR – Colorado
HJCL2008
Broke the
vase (WN 5)
Broke the
horse (WN 12)
Slow access
Slow access
Brown, ACL08
36
Hypotheses
Broke the
radio (WN 3)
DiscreteSenses
Broke the
vase (WN 5)
Broke the
horse (WN 12)
Slow access
Slow access
SharedRepresentn
CLEAR – Colorado
HJCL2008
Brown, ACL08
37
Hypotheses
Broke the
radio (WN 3)
Broke the
vase (WN 5)
Broke the
horse (WN 12)
DiscreteSenses
Slow access
Slow access
SharedRepresentn
Fast access
CLEAR – Colorado
HJCL2008
Brown, ACL08
38
Hypotheses
Broke the
radio (WN 3)
Broke the
vase (WN 5)
Broke the
horse (WN 12)
DiscreteSenses
Slow access
Slow access
SharedRepresentn
Fast access
Slow access
CLEAR – Colorado
HJCL2008
Brown, ACL08
39
Procedure


Semantic decision task
Judging semantic coherence of short phrases





banked the plane “makes sense”
hugged the juice doesn’t “make sense”
Pairs of phrases with the same verb
Primed with a sense in the first phrase
Sense in the second phrase was one of 4
degrees of relatedness to the first
CLEAR – Colorado
HJCL2008
Brown, ACL08
40
Materials – stimuli based on groupings
Prime
Target
Unrelated
banked the plane
banked the money
Distantly related
ran the track
ran the shop
Closely related
broke the glass
broke the radio
Same sense
cleaned the cup
cleaned the shirt
CLEAR – Colorado
HJCL2008
Brown, ACL08
41
Mean response time (in ms)
1500
1400
1300
1200
1100
1000
900
800
700
Sam e
CLEAR – Colorado
Close
HJCL2008
Distant
Unrelated
Brown, ACL08
42
Mean accuracy (% correct)
100
90
80
70
60
50
40
Sam e
CLEAR – Colorado
Close
HJCL2008
Distant
Unrelated
Brown, ACL08
43
Broke the
radio
Broke the
vase
Broke the
horse
DiscreteSenses
Slow access
Slow access
SharedRepresentn
Fast access
Slow access
CLEAR – Colorado
HJCL2008
Brown, ACL08
44
Broke the
radio

Broke the
vase
Broke the
horse
DiscreteSenses
Slow access
Slow access
SharedRepresentn
Fast access
1157 ms
Slow access
1330 ms
Closely related senses were processed more
quickly (t32=5.85; p<.0005)
CLEAR – Colorado
HJCL2008
Brown, ACL08
45
Shared-representation theory


Highly significant linear progression for
response time (F1,32=95.8; p<.0001) and accuracy
(F1,32=100.1; p<.0001).
Overlapping portions of meaning
representation



Closely related senses share a great deal
Distantly related senses share only a little
Unrelated senses share nothing
CLEAR – Colorado
HJCL2008
Brown, ACL08
46
Implications for WSD



Enumerating discrete senses may be a
convenient (necessary?) construct for
computers or lexicographers
Little information loss when combining closely
related senses
Distantly related senses are more like
homonyms, so they are more important to
keep separate
CLEAR – Colorado
HJCL2008
47
Computational model of the lexicon
based on annotation



Hypothesis: Syntactic structure overtly marks
very coarse-grained senses
Subsequently subdivided into more and more
fine-grained distinctions.
A measure of distance between the senses


The senses in a particular subdivision share
certain elements of meaning.
Computational model provided us with the
stimuli and the factors for the experiments.
CLEAR – Colorado
HJCL2008
48
Synergy between cognitive models and
computational models of the lexicon



Hierarchical computational model provides
stimuli and factors for response time
experiment
Confirmation of shared representation theory
provides support for computational model
and suggestions for richer representations
All based on Human Judgments!
CLEAR – Colorado
HJCL2008
49
Future work in psycholinguistics

Further analysis of categories of relatedness





Closely related pairs had 2 literal senses
Distantly related pairs often had 1 literal and 1
metaphoric sense
Corpus study of literal and metaphoric uses of
verbs and their frequency
Use for further experiments on how people store
and process sense distinctions
Annotation study looking at how well people can
make fine-grained sense distinctions in context
CLEAR – Colorado
HJCL2008
50
Future work in NLP

Improvements to WSD



Semi-supervised clustering of word senses



Dynamic dependency neighbors
(Dligach & Palmer, ACL08, ICSC 08)
Using language models for sentence selection
Hierarchical clustering? Soft clustering?
Against PB, VN, FN, Groupings, WN, etc.
Clustering of verb classes…..
CLEAR – Colorado
HJCL2008
51
Acknowledgments


We gratefully acknowledge the support of the
National Science Foundation Grant NSF0415923, Consistent Criteria for Word Sense
Disambiguation and DARPA-GALE via a
subcontract from BBN.
We thank Walter Kintsch and Al Kim for their
advice on the psycholinguistic experiments.
CLEAR – Colorado
HJCL2008
52
Leave behind, leave alone…

John left his keys at the restaurant.
We left behind all our cares during our vacation.
They were told to leave off their coats.
Leave the young fawn alone.
Leave the nature park just as you found it.
I left my shoes on when I entered their house.
When she put away the food she left out the pie.
Let's leave enough time to visit the museum.
He'll leave the decision to his wife.
When he died he left the farm to his wife.
I'm leaving our telephone and address with you.
CLEAR – Colorado
HJCL2008
53
Category criteria
WordNet
OED
Relatedness
Rating (0-3)
Unrelated pairs
Different
Unrelated
0-0.3
Distantly related
different
Related
0.7-1.4
Closely related
Different
1.7-2.4
Same sense
same
2.7-3.0
CLEAR – Colorado
HJCL2008
Brown, ACL08
54
Broke the
radio

Broke the
vase
Broke the
horse
DiscreteSenses
Slow access
Slow access
Shared-Repr
Fast access
1157 ms
91%
Slow access
1330 ms
71%
Closely related senses were processed more
quickly (t32=5.85; p<.0005) and accurately (t32=8.65;
p<.0001) than distantly related and unrelated
senses.
CLEAR – Colorado
HJCL2008
Brown, ACL08
55
Broke the
radio


Broke the
vase
Broke the
horse
DiscreteSenses
Slow access
Slow access
Shared-Repr
Fast access
1157 ms
91%
Slow access
1330 ms
71%
Closely related senses were processed more
quickly (t32=5.85; p<.0005) and accurately (t32=8.65;
p<.0001) than distantly related and unrelated
senses.
Distantly related senses were processed
more quickly (t32=2.38; p<.0001) and accurately
(t32=5.66; p<.0001) than unrelated senses.
CLEAR – Colorado
HJCL2008
Brown, ACL08
56