Sequence Classification with Neural Conditional Random Fields

TL;DR

This paper explores neural conditional random fields (CRFs) for sequence classification, demonstrating their ability to distinguish sequence types through calibrated class estimates, supported by experiments on complex tasks.

Contribution

It introduces neural CRFs for sequence classification and compares different models, highlighting their discriminative power beyond label accuracy.

Findings

Neural CRFs can effectively classify sequences regardless of label accuracy.

Calibrated class membership estimates improve sequence type discrimination.

Experimental results validate the effectiveness of neural CRFs on complex tasks.

Abstract

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.