Linear Transformations for Cross-lingual Sentiment Analysis
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 20 of its 38 references that are in the map. First posted on arXiv 15 Sep 2022.
Builds on
20 of 38 references.
References · 20
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
- 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
- 2016Enriching Word Vectors with Subword Informationcited by 1,578
- 2014Convolutional Neural Networks for Sentence Classificationcited by 1,124
- 2019How to Fine-Tune BERT for Text Classification?cited by 409
- 2019SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimizationcited by 253
- 2013Exploiting Similarities among Languages for Machine Translationcited by 187
- 2017A Survey Of Cross-lingual Word Embedding Modelscited by 142
- 2016Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classificationcited by 48
8 more
- 2018Multilingual Sentiment Analysis: An RNN-Based Framework for Limited Datacited by 19
- 2020Cross-Lingual Word Embeddings for Turkic Languagescited by 12
- 2016Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddingscited by 11
- 2020Improving Sentiment Analysis over non-English Tweets using Multilingual Transformers and Automatic Translation for Data-Augmentationcited by 9
- 2017Cross-Lingual Sentiment Analysis Without (Good) Translationcited by 7
- 2018Bilingual Sentiment Embeddings: Joint Projection of Sentiment Across Languagescited by 7
- 2021Are the Multilingual Models Better? Improving Czech Sentiment with Transformerscited by 7
- 2018Linear Transformations for Cross-lingual Semantic Textual Similaritycited by 3
Built on by
Citing papers per year: 2025: 2.
2 papers.