A SentiWordNet Strategy for Curriculum Learning in Sentiment Analysis
This work addresses sentiment analysis for NLP applications, presenting an incremental improvement by adapting an existing curriculum learning approach with a specific lexical resource.
The paper tackles sentiment analysis by applying curriculum learning driven by SentiWordNet to sequence training samples from easy to difficult, resulting in improved performance over random ordering and other curriculum strategies as assessed using convolutional, recurrent, and attention-based architectures on the Stanford Sentiment Treebank dataset.
Curriculum Learning (CL) is the idea that learning on a training set sequenced or ordered in a manner where samples range from easy to difficult, results in an increment in performance over otherwise random ordering. The idea parallels cognitive science's theory of how human brains learn, and that learning a difficult task can be made easier by phrasing it as a sequence of easy to difficult tasks. This idea has gained a lot of traction in machine learning and image processing for a while and recently in Natural Language Processing (NLP). In this paper, we apply the ideas of curriculum learning, driven by SentiWordNet in a sentiment analysis setting. In this setting, given a text segment, our aim is to extract its sentiment or polarity. SentiWordNet is a lexical resource with sentiment polarity annotations. By comparing performance with other curriculum strategies and with no curriculum, the effectiveness of the proposed strategy is presented. Convolutional, Recurrence, and Attention-based architectures are employed to assess this improvement. The models are evaluated on a standard sentiment dataset, Stanford Sentiment Treebank.