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

TL;DR

This paper enhances slot filling in spoken language understanding by integrating a novel word feature vector method with CNNs, leveraging 18 features and external libraries to improve performance on the ATIS dataset.

Contribution

It introduces a combined word feature vector approach with CNNs for slot filling, utilizing 18 features and external libraries to improve accuracy.

Findings

Improved slot filling accuracy on ATIS dataset

Outperforms traditional CNN models

Demonstrates effectiveness of feature set approach

Abstract

Slot filling is an important problem in Spoken Language Understanding (SLU) and Natural Language Processing (NLP), which involves identifying a user's intent and assigning a semantic concept to each word in a sentence. This paper presents a word feature vector method and combines it into the convolutional neural network (CNN). We consider 18 word features and each word feature is constructed by merging similar word labels. By introducing the concept of external library, we propose a feature set approach that is beneficial for building the relationship between a word from the training dataset and the feature. Computational results are reported using the ATIS dataset and comparisons with traditional CNN as well as bi-directional sequential CNN are also presented.