Sentence Level Recurrent Topic Model: Letting Topics Speak for Themselves
This work addresses topic modeling for applications like personalized conversation, but it appears incremental as it builds on existing RNN frameworks.
The paper tackles the problem of topic modeling by proposing SLRTM, a model that incorporates word order and topic coherence using RNNs, and it outperforms strong baselines on various tasks while enabling topic-to-sentence generation.
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.