Sequential Convolutional Neural Networks for Slot Filling in Spoken Language Understanding

06/24/2016
by   Ngoc Thang Vu, et al.
0

We investigate the usage of convolutional neural networks (CNNs) for the slot filling task in spoken language understanding. We propose a novel CNN architecture for sequence labeling which takes into account the previous context words with preserved order information and pays special attention to the current word with its surrounding context. Moreover, it combines the information from the past and the future words for classification. Our proposed CNN architecture outperforms even the previously best ensembling recurrent neural network model and achieves state-of-the-art results with an F1-score of 95.61 knowledge and resources.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/06/2016

Joint Online Spoken Language Understanding and Language Modeling with Recurrent Neural Networks

Speaker intent detection and semantic slot filling are two critical task...
research
06/18/2018

Combining Word Feature Vector Method with the Convolutional Neural Network for Slot Filling in Spoken Language Understanding

Slot filling is an important problem in Spoken Language Understanding (S...
research
09/17/2018

Robust Spoken Language Understanding via Paraphrasing

Learning intents and slot labels from user utterances is a fundamental s...
research
08/19/2018

Source-Critical Reinforcement Learning for Transferring Spoken Language Understanding to a New Language

To deploy a spoken language understanding (SLU) model to a new language,...
research
10/15/2019

VFNet: A Convolutional Architecture for Accent Classification

Understanding accent is an issue which can derail any human-machine inte...
research
10/29/2022

End-to-end Spoken Language Understanding with Tree-constrained Pointer Generator

End-to-end spoken language understanding (SLU) suffers from the long-tai...
research
10/16/2019

Joint Learning of Word and Label Embeddings for Sequence Labelling in Spoken Language Understanding

We propose an architecture to jointly learn word and label embeddings fo...

Please sign up or login with your details

Forgot password? Click here to reset