A Failure of Aspect Sentiment Classifiers and an Adaptive Re-weighting Solution
This addresses a critical failure in fine-grained sentiment analysis for applications like product reviews, though it is an incremental improvement over existing methods.
The paper identifies that existing aspect-based sentiment classifiers often fail to distinguish between different polarities for multiple aspects within a sentence, acting more like sentence-level classifiers. It proposes an adaptive re-weighting scheme that significantly improves performance on complex sentences, as demonstrated experimentally.
Aspect-based sentiment classification (ASC) is an important task in fine-grained sentiment analysis.~Deep supervised ASC approaches typically model this task as a pair-wise classification task that takes an aspect and a sentence containing the aspect and outputs the polarity of the aspect in that sentence. However, we discovered that many existing approaches fail to learn an effective ASC classifier but more like a sentence-level sentiment classifier because they have difficulty to handle sentences with different polarities for different aspects.~This paper first demonstrates this problem using several state-of-the-art ASC models. It then proposes a novel and general adaptive re-weighting (ARW) scheme to adjust the training to dramatically improve ASC for such complex sentences. Experimental results show that the proposed framework is effective \footnote{The dataset and code are available at \url{https://github.com/howardhsu/ASC_failure}.}.