Spoken Language Understanding in dialogue systems, using a 2-layer Markov Logic Network: improving semantic accuracy
Iván Meza, Sebastian Riedel, Oliver Lemon · 2008
We describe a two layer Markov Logic Net-work (MLN) model for the Spoken Lan-guage Understanding (SLU) task in dialogue systems. We augment the set of features used in Meza-Ruiz et al. (2008) with the help of off-the-shelf resources. We show that this setup increases the performance of the previous MLN models, which also out-perform the state-of-the art “Hidden Vector State ” (HVS) model of He and Young 2006. In particular the 2 layer approach produces more accurate sets of slot-values for user ut-terances (9 % improvement). 1