For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
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
Publication Date: 2017/12/01
Online ISSN: 1745-1361
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)>>
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.