Speech-Act Classification Using a Convolutional Neural Network Based on POS Tag and Dependency-Relation Bigram Embedding

Donghyun YOO  Youngjoong KO  Jungyun SEO  

IEICE TRANSACTIONS on Information and Systems   Vol.E100-D   No.12   pp.3081-3084
Publication Date: 2017/12/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2017EDL8083
Type of Manuscript: LETTER
Category: Natural Language Processing
speech-act classification,  dependency-relation,  convolutional neural network,  word embedding,  bigram embedding,  

Full Text: PDF(905.5KB)>>
Buy this Article

In this paper, we propose a deep learning based model for classifying speech-acts using a convolutional neural network (CNN). The model uses some bigram features including parts-of-speech (POS) tags and dependency-relation bigrams, which represent syntactic structural information in utterances. Previous classification approaches using CNN have commonly exploited word embeddings using morpheme unigrams. However, the proposed model first extracts two different bigram features that well reflect the syntactic structure of utterances and then represents them as a vector representation using a word embedding technique. As a result, the proposed model using bigram embeddings achieves an accuracy of 89.05%. Furthermore, the accuracy of this model is relatively 2.8% higher than that of competitive models in previous studies.