mlsanityData to 7 Oct 2026

Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification

arXiv 1606.01614 ↗First posted 6 Jun 2016cs.CLcited by 48

Not on the map. Why?

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.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Jun 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 24; 2022: 10; 2023: 2; 2024: 6; 2025: 3; 2026: 3.

48 papers.

Sort:

By area:

  1. 2023LEACE: Perfect linear concept erasure in closed formcited by 254
  2. 2022Test-Time Training with Masked Autoencoderscited by 208
  3. 2021XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyondcited by 114
  4. 2022Linear Adversarial Concept Erasurecited by 98
  5. 2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
  6. 2021Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Modelscited by 41
  7. 2021Multilingual Code-Switching for Zero-Shot Cross-Lingual Intent Prediction and Slot Fillingcited by 25
  8. 2021Bayesian Attention Belief Networkscited by 25
  9. 2021Code-Mixing on Sesame Street: Dawn of the Adversarial Polyglotscited by 23
  10. 2021MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learningcited by 21
  11. 2021AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NERcited by 17
  12. 2021Graph Neural Networks: Methods, Applications, and Opportunitiescited by 16
36 more
  1. 2021Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extractioncited by 16
  2. 2021Alignment Attention by Matching Key and Query Distributionscited by 14
  3. 2021Cross-lingual Text Classification with Heterogeneous Graph Neural Networkcited by 12
  4. 2021CogAlign: Learning to Align Textual Neural Representations to Cognitive Language Processing Signalscited by 11
  5. 2021A Dataset and Baselines for Multilingual Reply Suggestioncited by 9
  6. 2025Better LLM Reasoning via Dual-Playcited by 7
  7. 2021Latent-Optimized Adversarial Neural Transfer for Sarcasm Detectioncited by 6
  8. 2021Soft Layer Selection with Meta-Learning for Zero-Shot Cross-Lingual Transfercited by 5
  9. 2021Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extractioncited by 5
  10. 2024An Effective Deployment of Diffusion LM for Data Augmentation in Low-Resource Sentiment Classificationcited by 5
  11. 2021Efficient Variational Graph Autoencoders for Unsupervised Cross-domain Prerequisite Chainscited by 3
  12. 2022BioADAPT-MRC: Adversarial Learning-based Domain Adaptation Improves Biomedical Machine Reading Comprehension Taskcited by 3
  13. 2022Cross-lingual Adaptation for Recipe Retrieval with Mixupcited by 3
  14. 2022Domain Adaptation in Multilingual and Multi-Domain Monolingual Settings for Complex Word Identificationcited by 3
  15. 2021Neural Supervised Domain Adaptation by Augmenting Pre-trained Models with Random Unitscited by 2
  16. 2021Cross-Lingual Transfer Learning for Statistical Type Inferencecited by 2
  17. 2021KnowMAN: Weakly Supervised Multinomial Adversarial Networkscited by 2
  18. 2021Towards More Robust Natural Language Understandingcited by 2
  19. 2022Cross-lingual Word Embeddings in Hyperbolic Spacecited by 2
  20. 2022Linear Transformations for Cross-lingual Sentiment Analysiscited by 2
  21. 2023Parameter-Efficient Cross-lingual Transfer of Vision and Language Models via Translation-based Alignmentcited by 2
  22. 2024Provable Optimization for Adversarial Fair Self-supervised Contrastive Learningcited by 2
  23. 2024Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval-Augmented Generationcited by 2
  24. 2021A Conditional Generative Matching Model for Multi-lingual Reply Suggestioncited by 1
  25. 2022Log-linear Guardedness and its Implicationscited by 1
  26. 2026Cross-Language Speaker Attribute Prediction Using MIL and RLcited by 1
  27. 2021Zero-Resource Multi-Dialectal Arabic Natural Language Understandingcited by 0
  28. 2021Aligning Hotel Embeddings using Domain Adaptation for Next-Item Recommendationcited by 0
  29. 2022Cross-lingual Transfer Learning for Fake News Detector in a Low-Resource Languagecited by 0
  30. 2024Language-Independent Representations Improve Zero-Shot Summarizationcited by 0
  31. 2024Foundations of Multisensory Artificial Intelligencecited by 0
  32. 2024Distilling Monolingual and Crosslingual Word-in-Context Representationscited by 0
  33. 2025MSMO-ABSA: Multi-Scale and Multi-Objective Optimization for Cross-Lingual Aspect-Based Sentiment Analysiscited by 0
  34. 2025UniBERT: Adversarial Training for Language-Universal Representationscited by 0
  35. 2026RoIt-XMASA: Multi-Domain Multilingual Sentiment Analysis Dataset for Romanian and Italiancited by 0
  36. 2026XITE: Cross-lingual Interpolation for Transfer using Embeddingscited by 0