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

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.