As the emergence and the thriving development of social networks, a huge number of short texts are accumulated and need to be processed. Inferring latent topics of collected short texts is an essential task for understanding its hidden structure and predicting new contents. A biterm topic model (BTM) was recently proposed for short texts to overcome the sparseness of document-level word co-occurrences by directly modeling the generation process of word pairs. Stochastic inference algorithms based on collapsed Gibbs sampling (CGS) and collapsed variational inference have been proposed for BTM. However, they either require large computational complexity, or rely on very crude estimation that does not preserve sufficient statistics. In this work, we develop a stochastic divergence minimization (SDM) inference algorithm for BTM to achieve better predictive likelihood in a scalable way. Experiments show that SDM-BTM trained by 30% data outperforms the best existing algorithm trained by full data.

This letter proposes the Inference Algorithm through Effective Slot Allocation (ESA-IA). In ESA-IA, the tags which match the prefix of the reader's request-respond in the corresponding slot; the group of tags with an even number of 1's responds in slot 0, while the group with an odd number of 1's responds in slot 1. The proposed algorithm infers '00' and '11' if there are two collided bits in slot 0, while inferring '01' and '10' if there are two collided bits in slot 1. The ESA-IA decreases the time consumption for tag identification by reducing the overall number of queries.