Semantic Role Labeling via Instance-Based Learning

This paper demonstrates two methods to improve the performance of instancebased learning (IBL) algorithms for the problem of Semantic Role Labeling (SRL). Two IBL algorithms are utilized: k-Nearest Neighbor (kNN), and Priority Maximum Likelihood (PML) with a modified back-off combination method. The experimental data are the WSJ23 and Brown Corpus test sets from the CoNLL2005 Shared Task. It is shown that applying the Tree-Based PredicateArgument Recognition Algorithm (PARA) to the data as a preprocessing stage allows kNN and PML to deliver F1: 68.61 and 71.02 respectively on the WSJ23, and F1: 56.96 and 60.55 on the Brown Corpus; an increase of 8.28 in F1 measurement over the most recent published PML results for this problem (Palmer et al., 2005). Training times for IBL algorithms are very much faster than for other widely used techniques for SRL (e.g. parsing, support vector machines, perceptrons, etc); and the feature reduction effects of PARA yield testing and processing speeds of around 1.0 second per sentence for kNN and 0.9 second per sentence for PML respectively, suggesting that IBL could be a more practical way to perform SRL for NLP applications where it is employed; such as realtime Machine Translation or Automatic Speech Recognition.