Paper: Multilingual Dependency Learning: A Huge Feature Engineering Method to Semantic Dependency Parsing

ACL ID W09-1208
Title Multilingual Dependency Learning: A Huge Feature Engineering Method to Semantic Dependency Parsing
Venue International Conference on Computational Natural Language Learning
Session shared task
Year 2009
Authors
  • Hai Zhao (City University of Hong Kong, Kowloon Hong Kong; Soochow University, Suzhou China)
  • Wenliang Chen (National Institute of Information and Communications Technology, Kyoto Japan)
  • Chunyu Kitt (City University of Hong Kong, Kowloon Hong Kong)
  • Guodong Zhou (Soochow University, Suzhou China)

This paper describes our system about mul- tilingual semantic dependency parsing (SR- Lonly) for our participation in the shared task of CoNLL-2009. We illustrate that semantic dependency parsing can be transformed into a word-pair classification problem and im- plemented as a single-stage machine learning system. For each input corpus, a large scale feature engineering is conducted to select the best fit feature template set incorporated with a proper argument pruning strategy. The system achieved the top average score in the closed challenge: 80.47% semantic labeled F1 for the average score.