# Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification

arXiv: https://arxiv.org/abs/1606.01614 · HTML: https://mlsanity.com/paper/1606.01614/

## Key facts

- Cited by 48 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2016.

## Built on by (most cited first, 30 of 48)

- [LEACE: Perfect linear concept erasure in closed form](https://mlsanity.com/paper/2306.03819/) (2023)
- [Test-Time Training with Masked Autoencoders](https://mlsanity.com/paper/2209.07522/) (2022)
- [XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyond](https://mlsanity.com/paper/2104.12250/) (2021)
- [Linear Adversarial Concept Erasure](https://mlsanity.com/paper/2201.12091/) (2022)
- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models](https://mlsanity.com/paper/2103.08849/) (2021)
- [Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Filling](https://mlsanity.com/paper/2103.07792/) (2021)
- [Bayesian Attention Belief Networks](https://mlsanity.com/paper/2106.05251/) (2021)
- [Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglots](https://mlsanity.com/paper/2103.09593/) (2021)
- [MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning](https://mlsanity.com/paper/2104.07908/) (2021)
- [AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NER](https://mlsanity.com/paper/2106.02300/) (2021)
- [Graph Neural Networks: Methods, Applications, and Opportunities](https://mlsanity.com/paper/2108.10733/) (2021)
- [Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction](https://mlsanity.com/paper/2109.06798/) (2021)
- [Alignment Attention by Matching Key and Query Distributions](https://mlsanity.com/paper/2110.12567/) (2021)
- [Cross-lingual Text Classification with Heterogeneous Graph Neural Network](https://mlsanity.com/paper/2105.11246/) (2021)
- [CogAlign: Learning to Align Textual Neural Representations to Cognitive Language Processing Signals](https://mlsanity.com/paper/2106.05544/) (2021)
- [A Dataset and Baselines for Multilingual Reply Suggestion](https://mlsanity.com/paper/2106.02017/) (2021)
- [Better LLM Reasoning via Dual-Play](https://mlsanity.com/paper/2511.11881/) (2025)
- [Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection](https://mlsanity.com/paper/2104.09261/) (2021)
- [Soft Layer Selection with Meta-Learning for Zero-Shot Cross-Lingual Transfer](https://mlsanity.com/paper/2107.09840/) (2021)
- [Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction](https://mlsanity.com/paper/2109.02099/) (2021)
- [An Effective Deployment of Diffusion LM for Data Augmentation in Low-Resource Sentiment Classification](https://mlsanity.com/paper/2409.03203/) (2024)
- [Efficient Variational Graph Autoencoders for Unsupervised Cross-domain Prerequisite Chains](https://mlsanity.com/paper/2109.08722/) (2021)
- [BioADAPT-MRC: Adversarial Learning-based Domain Adaptation Improves Biomedical Machine Reading Comprehension Task](https://mlsanity.com/paper/2202.13174/) (2022)
- [Cross-lingual Adaptation for Recipe Retrieval with Mixup](https://mlsanity.com/paper/2205.03891/) (2022)
- [Domain Adaptation in Multilingual and Multi-Domain Monolingual Settings for Complex Word Identification](https://mlsanity.com/paper/2205.07283/) (2022)
- [Neural Supervised Domain Adaptation by Augmenting Pre-trained Models with Random Units](https://mlsanity.com/paper/2106.04935/) (2021)
- [Cross-Lingual Transfer Learning for Statistical Type Inference](https://mlsanity.com/paper/2107.00157/) (2021)
- [KnowMAN: Weakly Supervised Multinomial Adversarial Networks](https://mlsanity.com/paper/2109.07994/) (2021)
- [Towards More Robust Natural Language Understanding](https://mlsanity.com/paper/2112.02992/) (2021)

## Abstract (arXiv)

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.