Paper: Re-Ranking Models for Spoken Language Understanding

ACL ID E09-1024
Title Re-Ranking Models for Spoken Language Understanding
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 2009

Spoken Language Understanding aims at mapping a natural language spoken sen- tence into a semantic representation. In the last decade two main approaches have been pursued: generative and discrimi- native models. The former is more ro- bust to overfitting whereas the latter is more robust to many irrelevant features. Additionally, the way in which these ap- proaches encode prior knowledge is very different and their relative performance changes based on the task. In this pa- per we describe a machine learning frame- work where both models are used: a gen- erative model produces a list of ranked hy- potheses whereas a discriminative model based on structure kernels and Support Vector Machines, re-ranks such list. We tested our approach on the MEDIA cor- pus (human-machine dialogs) and on a ...