juliogonzalo brno

Sense clusters versus sense relations: 

Sense clusters versus sense relations Irina Chugur, Julio Gonzalo UNED (Spain)

Sense clusters vs. Sense relations: 

Sense clusters vs. Sense relations Arguments for sense clustering subtle distinctions produce noise in applications WN too fine-grained Remove predictable sense extensions?

Sense clusters vs. Sense relations: 

Sense clusters vs. Sense relations Arguments for sense clustering subtle distinctions produce noise in applications WN too fine-grained Remove predictable sense extensions? But... clusters are not absolute (e.g. metaphors in IR/MT) not really! Use them to infer and study systematic polysemy Polysemy relations are more informative and predictive WN rich sense distinctions permit empirical /quantitative studies on polysemy phenomena

Sense clusters vs. Sense relations: 

Sense clusters vs. Sense relations Arguments for sense clustering subtle distinctions produce noise in applications WN too fine-grained Remove predictable sense extensions? But... clusters are not absolute (e.g., are metaphors close?) not really! Use them to infer and study systematic polysemy Polysemy relations are more informative and predictive Annotation of semantic relations in 1000 wn nouns

Sense distinctions for IR: 

Sense distinctions for IR Helpful distinctions Spring season Fountain Metal device To jump Bank River bank Seat Financial institution Useless distinctions Bet Act of gambling Money risked on a gamble To gamble Bother Smth. or someone who causes trouble, a source of unhappiness An angry disturbance

1) Cluster evidence from Semcor: 

1) Cluster evidence from Semcor Hypothesis: if two senses tend to co-occur in the same documents, they are not good IR discriminators. Criterion: cluster senses that co-occur frequently in IR-Semcor collection. Example: fact 1 and fact 2 co-occur in 13 out of 171 docs. Fact 1. (a piece of information about circumstances that exist or events that have occurred) Fact 2. (a statement or assertion of verified information about something that is the case or has happened)

Cluster from Semcor: results: 

Cluster from Semcor: results Positive clusters: 507 (630 sense pairs) Threshold: #docs  2 with similar distribution of senses Precision: 70% (directly related to threshold) Negative clusters: 530 Threshold: #sense occurrences  8 Precision: 80%

2) Cluster evidence from parallel polysemy: 

2) Cluster evidence from parallel polysemy

2) Cluster evidence from parallel polysemy: 

2) Cluster evidence from parallel polysemy Groupe 9 Groupe 6 French German Band 2 Band 2

Parallel polysemy in EuroWordNet: 

Parallel polysemy in EuroWordNet English Spanish French German {child,kid}  {niño,crío,menor}{enfant,mineur}  {Kind} {male child,  {niño}  {enfant}  {Kind,Spross} Boy,child}

Comparison of clustering criteria: 

Comparison of clustering criteria

Clusters vs. semantic relations: 

Clusters vs. semantic relations Polysemy relations are more predictive!

Characterization of sense inventories for WSD: 

Characterization of sense inventories for WSD Given two senses of a word, How are they related? (polysemy relations) How closely? (sense proximity) In what applications should be distinguished? Given an individual sense of a word Should it be split into subsenses? (sense stability)

Slide14: 

Cross-Linguistic evidence Fine 40129 Mountains on the other side of the valley rose from the mist like islands, and here and there flecks of cloud as pale and <tag>fine</tag> as sea-spray, trailed across their sombre, wooded slopes. TRANSLATION: * *

Slide15: 

PL(same lexicalization|wi, wj)  Proximity(wi, wj)  Sense proximity (Resnik & Yarowsky)

Slide16: 

Sense Stability Stability(wi) 

Slide17: 

Experiment Design MAIN SET 44 Senseval-2 words (nouns and adjectives) 11 native/bilingual speakers of 4 languages Bulgarian Russian Spanish Urdu (control set: 12 languages, 5 families, 28 subjects)

Slide18: 

RESULTS: distribution of proximity indexes Average proximity = 0.29: same as Hector in Senseval 1!

Slide19: 

Results: distribution of stability indexes Average stability = 0.80

Slide20: 

distribution of homonyms ?

Slide21: 

distribution of metaphors

Slide22: 

distribution of metonymy Average proximity: target in source 0.64, source in target 0.37

Systematic polysemy  sense proximity: 

Systematic polysemy  sense proximity Positive and negative rules ? container / quantity music /dance animal / food language / people

Slide24: 

distribution of specialization/generalization

Annotation of 1000 wn nouns: 

Annotation of 1000 wn nouns Need for cluster here!

Typology of sense relations: 

Typology of sense relations Homonymy Metonymy Metaphor Specialization Generalization Equivalence fuzzy

Typology of sense relations: metonymy: 

Typology of sense relations: metonymy Homonymy Metonymy Metaphor Specialization Generalization Equivalence fuzzy target in source source in target Co-metonymy Animal-meat Animal-fur Tree-wood Object-color Plant-fruit People-language Action-duration Recipient-quantity ... Action-object Action-result Shape-object Plant-food/beverage Material-product ... Substance-agent

Typology of sense relations: metaphors: 

Typology of sense relations: metaphors Homonymy Metonymy Metaphor (182) Specialization Generalization Equivalence fuzzy object  object / person (47) person  person (21) physical action  abstract action (16) Physical property  abstract property (11) Animal  person (10) ...

Typology of sense relations: metaphors: 

Typology of sense relations: metaphors Homonymy Metonymy Metaphor (182) Specialization Generalization Equivalence fuzzy object  object / person (47) person  person (21) Source: historical, mythological, biblical character... profession, occupation, position ... Target: prototype person e.g. Adonis (greek mythology/handsome)

Conclusions: 

Conclusions Let’s annotate semantic relations between WN word senses!