Sentence Level Recurrent Topic Model: Letting Topics Speak for Themselves

2016/04/07 by Fei Tian, Tian, Fei, Bin Gao +5
Computer Science · Social Sciences · #Advanced Graph Neural Networks #Computation and Language (cs.CL) #Computational and Text Analysis Methods #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning (cs.LG) #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1604.02038

openalex publication_date 2016/04/07 · openalex created_date 2016/06/24 · openalex updated_date 2026/07/28

Abstract

We propose Sentence Level Recurrent Topic Model (SLRTM), a new topic model that assumes the generation of each word within a sentence to depend on both the topic of the sentence and the whole history of its preceding words in the sentence. Different from conventional topic models that largely ignore the sequential order of words or their topic coherence, SLRTM gives full characterization to them by using a Recurrent Neural Networks (RNN) based framework. Experimental results have shown that SLRTM outperforms several strong baselines on various tasks. Furthermore, SLRTM can automatically generate sentences given a topic (i.e., topics to sentences), which is a key technology for real world applications such as personalized short text conversation.

Citations

• Enhancing Navigation on Wikipedia with Social Tags
• Efficient Estimation of Word Representations in Vector Space
• Long Short-Term Memory
• Probabilistic Latent Semantic Indexing
• Distributed Representations of Sentences and Documents

Related

• LLM as Attention-Informed NTM and Topic Modeling as long-input Generation: Interpretability and long-Context Capability
• Recurrent Hierarchical Topic-Guided RNN for Language Generation
• Latent Topic Conversational Models
• SenGen: Sentence Generating Neural Variational Topic Model
• TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency