Paper: Multilingual Semantic Parsing with a Pipeline of Linear Classifiers

ACL ID W09-1216
Title Multilingual Semantic Parsing with a Pipeline of Linear Classifiers
Venue International Conference on Computational Natural Language Learning
Session shared task
Year 2009
Authors

I describe a fast multilingual parser for seman- tic dependencies. The parser is implemented as a pipeline of linear classifiers trained with support vector machines. I use only first or- der features, and no pair-wise feature combi- nations in order to reduce training and pre- diction times. Hyper-parameters are carefully tuned for each language and sub-problem. The system is evaluated on seven different languages: Catalan, Chinese, Czech, English, German, Japanese and Spanish. An analysis of learning rates and of the reliance on syn- tactic parsing quality shows that only modest improvements could be expected for most lan- guages given more training data; Better syn- tactic parsing quality, on the other hand, could greatly improve the results. Individual tun- ing of hyper-parameters is c...