Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/68912
Title: | 以稀疏潛在概念層改善基於變分自編碼架構的神經網絡主題模型 Improving Variational Auto-Encoder Based Neural Topic Model with Sparse Latent Concept Layer |
Authors: | Sheng-Yao Shen 沈聖堯 |
Advisor: | 黃鐘揚(Chung-Yang Huang) |
Keyword: | 潛在狄利克雷分配,主題模型,變分自編碼器, Latent Dirichlet Allocation,Topic Model,Variational Auto-encoder, |
Publication Year : | 2017 |
Degree: | 碩士 |
Abstract: | 此論文主要貢獻為提出一個簡單的基於變分自編碼器的主題模型,並提出有效的主題字選擇方式。通過將機率矩陣分解為主題矩陣與文字矩陣的乘積,我們引入了潛在概念 (Sparse Latent Concept, SLC) 作為主題與文字的語意向量空間維度,並基於主題具有「潛在概念的稀疏性」的假設,和以主題與文字的語意相似度作為主題字的選擇函數。實驗結果顯示,基於SLC的模型具有更高的平均主題一致性 (topic coherence)。 In this thesis, the primary contribution is proposing a simple variational auto-encoder based topic model, and effective topic word selection criteria. By decomposing the probability matrix into the product of a topic matrix and a word matrix, we introduce sparse latent concepts (SLC) as the dimensionalities of the semantic space of the topic and word vectors, improve the model based on the idea that a topic is represented as few latent concepts, and select topic words by semantic similarity between topic and word vectors. In the experiments, SLC-based model outperforms the non-SLC-based model in terms of average topic coherence. |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/68912 |
DOI: | 10.6342/NTU201702238 |
Fulltext Rights: | 有償授權 |
Appears in Collections: | 電機工程學系 |
Files in This Item:
File | Size | Format | |
---|---|---|---|
ntu-106-1.pdf Restricted Access | 2.67 MB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.