Paper: Multilingual Semantic Role Labelling with Markov Logic

ACL ID W09-1213
Title Multilingual Semantic Role Labelling with Markov Logic
Venue International Conference on Computational Natural Language Learning
Session shared task
Year 2009
Authors
  • Ivan Meza-Ruiz (University of Edinburgh, Edinburgh UK)
  • Sebastian Riedel (University of Tokyo, Tokyo Japan; Research Organization of Information and System, Japan)

This paper presents our system for the CoNLL 2009 Shared Task on Syntactic and Semantic Dependencies in Multiple Languages (Hajiˇc et al., 2009). In this work we focus only on the Semantic Role Labelling (SRL) task. We use Markov Logic to define a joint SRL model and achieve the third best average performance in the closed Track for SRLOnly systems and the sixth including for both SRLOnly and Joint systems. 1 Markov Logic Markov Logic (ML, Richardson and Domingos, 2006) is a Statistical Relational Learning language based on First Order Logic and Markov Networks. It can be seen as a formalism that extends First Or- derLogictoallowformulaethatcanbeviolatedwith some penalty. From an alternative point of view, it is an expressive template language that uses First Or- der Logic formulae to ins...