Re-Ranking Models Based-on Small Training Data for Spoken Language Understanding

The design of practical language applications by means of statistical approaches requires annotated data, which is one of the most critical constraint. This is particularly true for Spoken Dialog Systems since considerably domain-specific conceptual annotation is needed to obtain accurate Language Understanding models. Since data annotation is usually costly, methods to reduce the amount of data are needed. In this paper, we show that better feature representations serve the above purpose and that structure kernels provide the needed improved representation. Given the relatively high computational cost of kernel methods, we apply them to just re-rank the list of hypotheses provided by a fast generative model. Experiments with Support Vector Machines and different kernels on two different dialog corpora show that our re-ranking models can achieve better results than state-of-the-art approaches when small data is available.

• Type: Journal
• Year: 2009
• Where: EMNLP
• Authors: Marco Dinarelli, Alessandro Moschitti, Giuseppe Riccardi
• Keywords: Domain-specific Conceptual Annotation, EMNLP 2009, Fast Generative Model, Natural Language Processing, Practical Language Applications