Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification
This addresses sentiment classification for low-resource languages, which is an incremental advance in domain-specific natural language processing.
The paper tackles cross-lingual sentiment classification by proposing an Adversarial Deep Averaging Network (ADAN) to transfer knowledge from a resource-rich source language to low-resource languages using unlabeled data, achieving significant improvements over state-of-the-art systems in experiments on Chinese and Arabic.
In recent years great success has been achieved in sentiment classification for English, thanks in part to the availability of copious annotated resources. Unfortunately, most languages do not enjoy such an abundance of labeled data. To tackle the sentiment classification problem in low-resource languages without adequate annotated data, we propose an Adversarial Deep Averaging Network (ADAN) to transfer the knowledge learned from labeled data on a resource-rich source language to low-resource languages where only unlabeled data exists. ADAN has two discriminative branches: a sentiment classifier and an adversarial language discriminator. Both branches take input from a shared feature extractor to learn hidden representations that are simultaneously indicative for the classification task and invariant across languages. Experiments on Chinese and Arabic sentiment classification demonstrate that ADAN significantly outperforms state-of-the-art systems.