tailieunhanh - Báo cáo khoa học: "Re-Ranking Models For Spoken Language Understanding Marco Dinarelli University of Trento Italy"

Spoken Language Understanding aims at mapping a natural language spoken sentence into a semantic representation. In the last decade two main approaches have been pursued: generative and discriminative models. The former is more robust to overfitting whereas the latter is more robust to many irrelevant features. Additionally, the way in which these approaches encode prior knowledge is very different and their relative performance changes based on the task. | Re-Ranking Models For Spoken Language Understanding Marco Dinarelli University of Trento Italy dinarelli@ Alessandro Moschitti University of Trento Italy moschitti@ Giuseppe Riccardi University of Trento Italy riccardi@ Abstract Spoken Language Understanding aims at mapping a natural language spoken sentence into a semantic representation. In the last decade two main approaches have been pursued generative and discriminative models. The former is more robust to overfitting whereas the latter is more robust to many irrelevant features. Additionally the way in which these approaches encode prior knowledge is very different and their relative performance changes based on the task. In this paper we describe a machine learning framework where both models are used a generative model produces a list of ranked hypotheses whereas a discriminative model based on structure kernels and Support Vector Machines re-ranks such list. We tested our approach on the MEDIA corpus human-machine dialogs and on a new corpus human-machine and humanhuman dialogs produced in the European LUNA project. The results show a large improvement on the state-of-the-art in concept segmentation and labeling. 1 Introduction In Spoken Dialog Systems the Language Understanding module performs the task of translating a spoken sentence into its meaning representation based on semantic constituents. These are the units for meaning representation and are often referred to as concepts. Concepts are instantiated by sequences of words therefore a Spoken Language Understanding SLU module finds the association between words and concepts. In the last decade two major approaches have been proposed to find this correlation i generative models whose parameters refer to the joint probability of concepts and constituents and ii discriminative models which learn a classification function to map words into concepts based on geometric and statistical properties. An example of .