Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification

Domain:

natural language processing

Record type:

paper
Creator:
CheSun, YuAthCar
Host:avatar
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. TACL journal version

Visit

arxiv.org

Tasks

sentiment analysistext classificationtransfer learning

Tags

Computation and Language

Similar

Deep Persian sentiment analysis: Cross-lingual training for low-resource languagesCross-Multilingual, Cross-Lingual and Monolingual Transfer Learning For Arabic Dialect Sentiment ClassificationAutomated Cross-Lingual Semantic Alignment via Hierarchical Generative Adversarial Networks for Endangered Language DocumentationDeep learning-based sentiment classification in Amharic using multi-lingual datasetsGradient-based adversarial fine-tuning for XLM-R robustness in zero-shot cross-lingual classificationAdversarial Example Detection by Classification for Deep Speech Recognition

Deep Persian sentiment analysis: Cross-lingual training for low-resource languages

With the advent of deep neural models in natural language processing tasks, having a large amount of

Cross-Multilingual, Cross-Lingual and Monolingual Transfer Learning For Arabic Dialect Sentiment Classification

Abstract Transfer learning have recently proven to be very powerful in diverse Natural lan

Automated Cross-Lingual Semantic Alignment via Hierarchical Generative Adversarial Networks for Endangered Language Documentation

**Abstract:** Low-resource languages face an urgent threat of extinction, largely due to limited doc

Deep learning-based sentiment classification in Amharic using multi-lingual datasets

The analysis of emotions expressed in natural language text, also known as sentiment analysis, is a

Gradient-based adversarial fine-tuning for XLM-R robustness in zero-shot cross-lingual classification

Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potentia

Adversarial Example Detection by Classification for Deep Speech Recognition

Machine Learning systems are vulnerable to adversarial attacks and will highly likely produce incorr