Sequential Convolutional Neural Networks for Slot Filling in Spoken Language Understanding

TL;DR

This paper introduces a novel convolutional neural network architecture for slot filling in spoken language understanding, leveraging context and outperforming previous models with state-of-the-art accuracy.

Contribution

The paper presents a new CNN architecture that effectively captures context for sequence labeling in spoken language understanding, achieving superior results without extra linguistic resources.

Findings

Outperforms previous RNN ensemble models

Achieves 95.61% F1-score on ATIS dataset

Does not require additional linguistic resources

Abstract

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% on the ATIS benchmark dataset without using any additional linguistic knowledge and resources.