Sequence Classification with Neural Conditional Random Fields
This work addresses sequence classification for sensor data analysis, but it appears incremental as it adapts existing CRF methods with neural networks.
The paper tackles the problem of sequence classification using neural conditional random fields (CRFs), proposing that CRFs can serve as discriminative models for distinguishing sequence types by calibrating class membership estimates, and it presents experiments on complex tasks to support this claim.
The proliferation of sensor devices monitoring human activity generates voluminous amount of temporal sequences needing to be interpreted and categorized. Moreover, complex behavior detection requires the personalization of multi-sensor fusion algorithms. Conditional random fields (CRFs) are commonly used in structured prediction tasks such as part-of-speech tagging in natural language processing. Conditional probabilities guide the choice of each tag/label in the sequence conflating the structured prediction task with the sequence classification task where different models provide different categorization of the same sequence. The claim of this paper is that CRF models also provide discriminative models to distinguish between types of sequence regardless of the accuracy of the labels obtained if we calibrate the class membership estimate of the sequence. We introduce and compare different neural network based linear-chain CRFs and we present experiments on two complex sequence classification and structured prediction tasks to support this claim.