Contextual domain classification in spoken language understanding systems using recurrent neural network

In a multi-domain, multi-turn spoken language understanding session, information from the history often greatly reduces the ambiguity of the current turn. In this paper, we apply the recurrent neural network (RNN) to exploit contextual information for query domain classification. The Jordan-type RNN...

Full description

Saved in:
Bibliographic Details
Main Authors: Puyang Xu, Sarikaya, Ruhi
Format: Conference Proceeding
Language:English
Subjects:
Context
contextual domain classification
Error analysis
Feature extraction
Predictive models
Recurrent neural network
Recurrent neural networks
Support vector machines
Vectors
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In a multi-domain, multi-turn spoken language understanding session, information from the history often greatly reduces the ambiguity of the current turn. In this paper, we apply the recurrent neural network (RNN) to exploit contextual information for query domain classification. The Jordan-type RNN directly sends the vector of output distribution to the next query turn as additional input features to the convolutional neural network (CNN). We evaluate our approach against SVM with and without contextual features. On our contextually labeled dataset, we observe a 1.4% absolute (8.3% relative) improvement in classification error rate over the non-contextual SVM, and 0.9% absolute (5.5% relative) improvement over the contextual SVM.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2014.6853573