Please use this identifier to cite or link to this item:
Title: Topic-Aware Deep Compositional Models for Sentence Classification
Authors: Zhao, Rui
Mao, Kezhi
Keywords: Machine learning
Natural language processing
Issue Date: 2017
Source: Zhao, R., & Mao, K. (2017). Topic-Aware Deep Compositional Models for Sentence Classification. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 25(2), 248-260.
Series/Report no.: IEEE/ACM Transactions on Audio, Speech, and Language Processing
Abstract: In recent years, deep compositional models have emerged as a popular technique for representation learning of sentence in computational linguistic and natural language processing. These models normally train various forms of neural networks on top of pretrained word embeddings using a task-specific corpus. However, most of these works neglect the multisense nature of words in the pretrained word embeddings. In this paper we introduce topic models to enrich the word embeddings for multisenses of words. The integration of the topic model with various semantic compositional processes leads to topic-aware convolutional neural network and topic-aware long short term memory networks. Different from previous multisense word embeddings models that assign multiple independent and sense-specific embeddings to each word, our proposed models are lightweight and have flexible frameworks that regard word sense as the composition of two parts: a general sense derived from a large corpus and a topic-specific sense derived from a task-specific corpus. In addition, our proposed models focus on semantic composition instead of word understanding. With the help of topic models, we can integrate the topic-specific sense at word-level before the composition and sentence-level after the composition. Comprehensive experiments on five public sentence classification datasets are conducted and the results show that our proposed topic-aware deep compositional models produce competitive or better performance than other text representation learning methods.
ISSN: 2329-9290
DOI: 10.1109/TASLP.2016.2632521
Schools: School of Electrical and Electronic Engineering 
Rights: © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: [].
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:EEE Journal Articles

Files in This Item:
File Description SizeFormat 
Topic-Aware Deep Compositional Models for Sentence Classification.pdf934.27 kBAdobe PDFThumbnail

Citations 20

Updated on Jun 14, 2024

Web of ScienceTM
Citations 20

Updated on Oct 28, 2023

Page view(s) 20

Updated on Jun 20, 2024

Download(s) 5

Updated on Jun 20, 2024

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.