Continual Learning with Knowledge Transfer for Sentiment Classification
This addresses the problem of knowledge retention and transfer in incremental learning for sentiment analysis, though it appears incremental in method.
The paper tackles continual learning for sentiment classification by proposing KAN, a technique that improves accuracy for both new and old tasks through forward and backward knowledge transfer, as demonstrated in experiments.
This paper studies continual learning (CL) for sentiment classification (SC). In this setting, the CL system learns a sequence of SC tasks incrementally in a neural network, where each task builds a classifier to classify the sentiment of reviews of a particular product category or domain. Two natural questions are: Can the system transfer the knowledge learned in the past from the previous tasks to the new task to help it learn a better model for the new task? And, can old models for previous tasks be improved in the process as well? This paper proposes a novel technique called KAN to achieve these objectives. KAN can markedly improve the SC accuracy of both the new task and the old tasks via forward and backward knowledge transfer. The effectiveness of KAN is demonstrated through extensive experiments.