Professional Documents
Culture Documents
Acl 2013 Slides
Acl 2013 Slides
Semantic Similarity
Semantic Similarity
Semantic Similarity
Sentence level
Semantic Similarity
Semantic Similarity
Word level
Locuacious Talkative
Lexical substitution
(McCarthy and Navigli, 2009)
Semantic Similarity
Semantic Similarity
Sense level
Semantic Similarity
Sense level
Resnik (1995)
Sussna (1993, 1997) Wu and Palmer (1994)
Resnik (1995)
Sussna (1993, 1997) Wu and Palmer (1994)
Resnik (1995)
Sussna (1993, 1997) Wu and Palmer (1994)
Resnik (1995)
Sussna (1993, 1997) Wu and Palmer (1994)
Resnik (1995)
Sussna (1993, 1997) Wu and Palmer (1994)
Contribution
Contribution
Contribution
Contribution
Advantage 1
Unified representation
Advantage 2
Advantage 3
Sense-level operation
Outline
Semantic Signature
Semantic Signature
Semantic Signature
Semantic Signature
Semantic Signature
Semantic Signature
Semantic Signature
Semantic Signature
Semantic Signature
Semantic Signature
Semantic Signature
Semantic Signature
over all synsets in WordNet
. . .
Semantic Signature
over all synsets in WordNet
. . .
Semantic Signature
over all synsets in WordNet
. . .
Semantic Signature
Semantic Signature
Semantic Signature
Semantic Signature
Semantic Signature
Semantic Signature
Personalized PageRank
Personalized PageRank
Personalized PageRank
Personalized PageRank
1 2 woman n fry v
food n
Personalized PageRank
1 2 woman n fry v
food n
Personalized PageRank
1 2 woman n fry v
food n
2 fry v
Personalized PageRank
1 2 woman n fry v
food n
2 fry v 1
food n
Personalized PageRank
1 2 woman n fry v
food n
2 fry v 1 1 woman n
food n
Personalized PageRank
1 2 woman n fry v
food n
2 fry v 1 1 woman n
food n
1 food n
1 beveragen 2 food n
1 fat n
fry v
1 food n
1 beveragen 2 food n
1 fat n
fry v
Cosine
= 4
= 4
= 4
Alignment-based disambiguation
Alignment-based disambiguation
Alignment-based disambiguation
Alignment-based disambiguation
Alignment-based disambiguation
Alignment-based disambiguation
1 manager n 2 manager n
worker n
1 employee n
boss 1 n boss 2 n
. . .
worker n
. . .
. . .
Alignment-based disambiguation
1 manager n 2 manager n
worker n
1 employee n
boss 1 n boss 2 n
. . .
worker n
. . .
. . .
Alignment-based disambiguation
1 employee n
boss 1 n boss 2 n
. . .
manager n
. . .
manager n
terminate 4 v
Alignment-based disambiguation
1 employee n
boss 1 n boss 2 n
. . .
manager n
. . .
manager n
terminate 4 v
Alignment-based disambiguation
0.5
1 employee n
boss 1 n boss 2 n
. . .
manager n
. . .
manager n
terminate 4 v
Alignment-based disambiguation
0.5
1 employee n
boss 1 n boss 2 n
. . .
manager n
. . .
manager n
terminate 4 v
Alignment-based disambiguation
0.5 0.3
1 employee n
boss 1 n boss 2 n
. . .
manager n
. . .
manager n
terminate 4 v
Alignment-based disambiguation
0.5 0.3 0.3
1 employee n
boss 1 n boss 2 n
. . .
manager n
. . .
manager n
terminate 4 v
Alignment-based disambiguation
1 manager n 2 manager n
worker n
1 employee n
boss 1 n boss 2 n
. . .
worker n
. . .
. . .
Alignment-based disambiguation
1 manager n 2 manager n
worker n
1 employee n
boss 1 n boss 2 n
. . .
worker n
. . .
. . .
Outline
Experiments
Experiments
Experiments
Experiment 1
Experiment 1
UKP2 (Br et al., 2012) TLSim and TLSyn (ari et al., 2012)
Experiment 1
Experiment 1
String-based features
Longest common substring Longest common subsequence Greedy string tiling Character/word n-grams
Experiment 1
Experiment 1
Experiments
Experiment 2
Experiment 2
Experiment 2
75
80
85
90
95
100
Scale of 0 4
Experiments
Experiment 3
Experiment 3
Experiment 3
Experiment 3
Experiment 3
(Kilgarriff, 2001)
about 16000 sense pairs (Noun) about 31000 sense pairs (Verb)
Experiment 3
if similarity
Experiment 3
if similarity
Experiment 3
Verb
0.37 0.45 0.53
0.54
0.52
0.41
Experiment 3
0.37
0.42
0.47 0.47 0.44
Conclusions
A unified approach for computing semantic similarity for any pair of lexical items
Experiments with SOA performance
Sense level (sense coarsening) Word level (synonymy recognition and judgment) Sentence level (Semantic Textual Similarity)
Future Direction
Larger sense inventories (e.g., BabelNet)
Future Direction
Larger sense inventories (e.g., BabelNet)
Cross-level semantic similarity
Future Direction
Larger sense inventories (e.g., BabelNet)
Cross-level semantic similarity Create datasets for cross-level similarity
Future Semeval task?
expression
1 thank_you n
2 sensing n
thanks
1
1 heed v
gratitude
listen audio-lingual
1
v
2 ear n
listening
1 auscultation n
listen
1 v
hearing
STS-13
System Dkpro TakeLab ADW (STS-13) ADW (All) GP ADW (All) LR HDL 0.735 0.486 0.621 0.717 0.667 OnWN 0.735 0.633 0.511 0.697 0.735 FNWN 0.341 0.269 0.446 0.411 0.409 SMT 0.323 0.279 0.384 0.272 0.374 mean 0.565 0.434 0.502 0.538 0.565 Rank 6 58 34 20 6