Multilingual dependency learning

Abstract

This paper describes our system about multilingual 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 implemented 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.