This paper presents a RNN-based language model that is designed to capture a long-range semantic dependency. The proposed model is a simple and elegant, and yields sensible topics.
The key insight of this work is the difference between semantic and syntax. Semantic is relating to an over structure and information of the given context. If we are given a document, its semantic is a theme or topic. Semantic is meant to capture a global meaning of the context. We need to see enough words to understand its semantics.
In contrast, a syntax is dealt with local information. The likelihood of the current word heavily depends on the preceding words. This local information depends on the word order whereas the global information does not depend on word order.
This paper points out the weakness in probabilistic topic models such as LDA such as its lack of word order, its poor performance on word prediction. If we use bigram or trigram then these higher order models become intractable. Furthermore, LDA does not model stopwords very well because LDA is based on word co-occurrence. Stopwords tend to appear everywhere because stopwords do not carry semantic information but it acts as a filler to make the language more readable. Thus, when training LDA, the stopwords are usually discarded during the preprocessing.
RNN-based language models attempt to capture sequential information. It models a word joint distribution as . The Markov assumption is necessary to keep the inference tractable. The shortcoming is the limitation of the context windows. The higher order Markov assumption makes an inferencing becomes more difficult.
The neural network language model avoids Markov assumption by modeling a conditional probability where . Basically, is a summarization of the preceding words and it uses this information to predict the current word. The RNN-based language model works pretty well but it has difficulty with long-range dependency due to the difficulty in optimization and overfitting.
Combining the advantage from both topic modeling and RNN-based is the contribution of this paper. The topic model will be used as a bias to the learned word conditional probability. They chose to make the topic vector as a bias because they don’t want to mix it up with the hidden state of RNN that includes stop words.
The model has a binary switch variable. When it encounters a stopword, the switch is off and disable a topic vector. The switch is on otherwise. The word probability is defined as follows:
The switch variable, turn on and off the topic vector .
This model is an end-to-end network, meaning that it will jointly learn topic vectors and local state from RNN. The topic vector is coupled with RNN’s state so the local dynamic from word sequence will influence the topic vector and wise verse.
RNN can be replaced with GRU or LSTM. The paper shows that using GRU yields the best perplexity on Penn Treebank (PTB) dataset. The learned representation can be used to as a feature for many tasks including sentiment analysis where we want to classify positive and negative reviews on IMDB dataset.
I found this model is simple and elegantly combine VAE with RNN. The motivation is clear and we can see why using contextual information learned from VAE will improve the quality of the representation.
https://arxiv.org/abs/1611.01702 (ICLR 2017 – Poster)