Linear Transformations for Cross-lingual Sentiment Analysis
arXiv:2209.07244 · doi:10.1007/978-3-031-16270-1_11
Abstract
This paper deals with cross-lingual sentiment analysis in Czech, English and French languages. We perform zero-shot cross-lingual classification using five linear transformations combined with LSTM and CNN based classifiers. We compare the performance of the individual transformations, and in addition, we confront the transformation-based approach with existing state-of-the-art BERT-like models. We show that the pre-trained embeddings from the target domain are crucial to improving the cross-lingual classification results, unlike in the monolingual classification, where the effect is not so distinctive.
arXiv commentAccepted to TSD 2022
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- Exploiting Similarities among Languages for Machine Translation
- Massively Multilingual Word Embeddings
- A Survey Of Cross-lingual Word Embedding Models
- SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization
- Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings
- Multilingual Sentiment Analysis: An RNN-Based Framework for Limited Data
- Cross-Lingual Sentiment Analysis Without (Good) Translation
- Cross-Lingual Word Embeddings for Turkic Languages