220 likes | 315 Views
Language & Interaction Research. A Joint Model of Implicit Arguments for Nominal Predicates. Matthew Gerber and Joyce Y. Chai Department of Computer Science Michigan State University East Lansing, Michigan, USA {gerberm2,jchai}@cse.msu.edu. Robert Bart
E N D
Language & Interaction Research A Joint Model of Implicit Arguments for Nominal Predicates Matthew Gerber and Joyce Y. Chai Department of Computer Science Michigan State University East Lansing, Michigan, USA {gerberm2,jchai}@cse.msu.edu Robert Bart Computer Science and Engineering University of Washington Seattle, Washington, USA rbart@cs.washington.edu
Implicit Arguments Georgia-Pacific and Nekoosa produce market pulp, containerboard and white paper. The goods could be manufactured closer to customers, saving shipping costs. • What can traditional SRL systems tell us?
Implicit Arguments Georgia-Pacific and Nekoosa produce market pulp, containerboard and white paper. The goods could be manufactured closer to customers, saving shipping costs. • What can traditional SRL systems tell us? • Who is the producer? • What is produced?
Implicit Arguments Georgia-Pacific and Nekoosa produce market pulp, containerboard and white paper. The goods could be manufactured closer to customers, saving shipping costs. • What can traditional SRL systems tell us? • Who is the producer? • What is produced? • What is manufactured? • But that’s not the whole story… • Who is the manufacturer?
Implicit Arguments Georgia-Pacific and Nekoosa produce market pulp, containerboard and white paper. The goods could be manufactured closer to customers, saving shipping costs. • What can traditional SRL systems tell us? • Who is the producer? • What is produced? • What is manufactured? • But that’s not the whole story… • Who is the manufacturer? • Who ships?
Implicit Arguments Georgia-Pacific and Nekoosa produce market pulp, containerboard and white paper. The goods could be manufactured closer to customers, saving shipping costs. • What can traditional SRL systems tell us? • Who is the producer? • What is produced? • What is manufactured? • But that’s not the whole story… • Who is the manufacturer? • Who ships what?
Implicit Arguments Georgia-Pacific and Nekoosa produce market pulp, containerboard and white paper. The goods could be manufactured closer to customers, saving shipping costs. • What can traditional SRL systems tell us? • Who is the producer? • What is produced? • What is manufactured? • But that’s not the whole story… • Who is the manufacturer? • Who ships what to whom? Implicit arguments
Model Formulation (Gerber and Chai, 2010) c1 c2 Georgia-Pacific and Nekoosa produce market pulp, containerboard and white paper. The goods could be manufactured closer to customers, saving shipping costs. c3 • Candidate selection • PropBank/NomBank arguments • Two-sentence candidate window • Coreference chaining • Binary classification function Assume independent arguments
Are Arguments Independent? The president is struggling to manage the country’s economy. If he cannot get it under control, loss of the next election might result.
Are Arguments Independent? The president is struggling to manage the country’s economy. If he cannot get it under control, loss of the next election might result. • What entity might lose? • Economies lose jobs, value, etc. • Presidents lose votes, allegiance, etc. • Implicit arguments are not independent • A joint model would be more natural
Related Work • Joint verbal SRL (Toutanova et al. (2008)) • Re-rank full argument structures • Joint label sequence • [arg0, Predicate, arg1] • [arg0, Predicate, arg0] • Joint selectional preferences (Ritter et al. (2010)) • [Arg0 economy] [Predicate lost] [Arg1 jobs] • [Arg0 economy] [Predicate lost] [Arg1 election] • Relies on TextRunner extraction system
TextRunner • Open Information Extraction (OIE) database • Query • Arg0: ? • Predicate: lose • Arg1: election • Answer • [Arg0 The president] [Predicate lost] [Arg1 the election]. • Use TextRunner to identify joint implicit arguments
Joint Implicit Argument Model The president is struggling to manage the country’s economy. If he doesn’t succeed by the next election, a loss might result. • Model joint occurrence of iarg0 and iarg1 • Consider all possible candidate assignments
Joint Implicit Argument Model • Using TextRunner queries • Query 1: <president, lose, ?> • <Kenyan president, lose, election> • <president, lose, ally> • … • Query 2: <?, lose, election> • <Republican party, lose, election> • <president, lose, election> • … • Match rank • Match similarity • Local model scores
Evaluation Setting • Data created by Gerber and Chai (2010) • 1,200 annotations of 10 predicates • Only test instances that take iarg0 and iarg1 • Ten-fold cross-validation • Baseline: independent classification model
Evaluation Setting • Methodology (Ruppenhofer et al., 2010) • Ground-truth implicit arguments: • Predicted implicit argument: • Prediction score: • P: total prediction score / prediction count • R: total prediction score / true implicit positions Georgia-Pacific and Nekoosa produce market pulp, containerboard and white paper. The goods could be manufactured closer to customers, saving shipping costs.
Evaluation Results • Overall results • Baseline F1: 72.2% • Joint F1: 73.1% • Per-predicate
Example Improvement Big investors can decide to ride out market storms without selling stock. They often do that because stocks have proved to be the best-performing investment, attracting $1 trillion. [iarg1 money] • What was invested? • Who invested? • Baseline (independent) model is incorrect • Joint model is correct
Example Improvement Big investors can decide to ride out market storms without selling stock. They often do that because stocks have proved to be the best-performing investment, attracting $1 trillion. [iarg1 money] • Query 1: <investor, invest, ?> • Answers: money, amount, million • Query 2: <?, invest, money> • Answers: government, business, investor
Summary • Implicit arguments • Frequent • Nearby • Can be automatically recovered • Semantic arguments are not independent • OIE can help identify argument dependencies • Joint model can recover from simple errors
Future Work • Extension to other predicates • Only 10 are currently considered • Extension to other argument positions • iarg2 and iarg3 are also common • Computational complexity • Exhaustive search is intractable • Heuristic search • Gibbs sampling for joint inference
Questions? Matthew Gerber: gerberm2@msu.edu