شماره ركورد كنفرانس :
3540
عنوان مقاله :
Discriminative Spoken Language Understanding Using Statistical Machine Translation Alignment Methods
Author/Authors :
Mohammad Aliannejadi Amirkabir University of Technology, Tehran, Iran , Shahram Khadivi Amirkabir University of Technology, Tehran, Iran , Saeed Shiry Amirkabir University of Technology, Tehran, Iran , Mohammad Hadi Bokaei Sharif University of Technology, Tehran, Iran
كليدواژه :
natural language processing , spoken language understanding , statistical machine trans- lation
عنوان كنفرانس :
همايش بين المللي هوش مصنوعي و پردازش سيگنال
چكيده لاتين :
In this paper, we study the discriminative modeling of Spo-
ken Language Understanding (SLU) using Conditional Random Fields
(CRF). Previous discriminative approaches to SLU have been dependent
on n-gram features.We have used Statistical Machine Translation (SMT)
alignment methods to align the abstract labels, and consider those align-
ments as the labels of the aligned words. Using the proposed alignment
method and state transition features, the model performance has im-
proved. Furthermore, we have compared the proposed method with two
baseline approaches; Hidden Vector States (HVS) and baseline-CRF. The
results show that for the F-measure the proposed method outperforms
HVS by 1:74% and baseline-CRF by 1:7% on ATIS corpus.
