Exploiting Position Bias for Robust Aspect Sentiment Classification
This addresses robustness problems for aspect sentiment classification, but it is incremental as it enhances existing models rather than introducing a new paradigm.
The paper tackles the robustness issue in aspect sentiment classification models, which fail in out-of-domain or adversarial scenarios by mis-attending to irrelevant words, and proposes mechanisms to exploit position bias, resulting in large improvements in robustness and effectiveness as demonstrated in experiments.
Aspect sentiment classification (ASC) aims at determining sentiments expressed towards different aspects in a sentence. While state-of-the-art ASC models have achieved remarkable performance, they are recently shown to suffer from the issue of robustness. Particularly in two common scenarios: when domains of test and training data are different (out-of-domain scenario) or test data is adversarially perturbed (adversarial scenario), ASC models may attend to irrelevant words and neglect opinion expressions that truly describe diverse aspects. To tackle the challenge, in this paper, we hypothesize that position bias (i.e., the words closer to a concerning aspect would carry a higher degree of importance) is crucial for building more robust ASC models by reducing the probability of mis-attending. Accordingly, we propose two mechanisms for capturing position bias, namely position-biased weight and position-biased dropout, which can be flexibly injected into existing models to enhance representations for classification. Experiments conducted on out-of-domain and adversarial datasets demonstrate that our proposed approaches largely improve the robustness and effectiveness of current models.