Cross-lingual Sentiment Classification Research Articles

A comparative study of cross-lingual sentiment analysis

This paper presents a detailed comparative study of the zero-shot cross-lingual sentiment analysis. Namely, we use modern multilingual Transformer-based models and linear transformations combined with CNN and LSTM neural networks. We evaluate their performance in Czech, French, and English. We aim to compare and assess the models’ ability to transfer knowledge across languages and discuss the trade-off between their performance and training/inference speed. We build strong monolingual baselines comparable with the current SotA approaches, achieving state-of-the-art results in Czech (96.0% accuracy) and French (97.6% accuracy). Next, we compare our results with the latest large language models (LLMs), i.e., Llama 2 and ChatGPT.We show that the large multilingual Transformer-based XLM-R model consistently outperforms all other cross-lingual approaches in zero-shot cross-lingual sentiment classification, surpassing them by at least 3%. Next, we show that the smaller Transformer-based models are comparable in performance to older but much faster methods with linear transformations. The best-performing model with linear transformation achieved an accuracy of 92.1% on the French dataset, compared to 90.3% received by the smaller XLM-R model. Notably, this performance is achieved with just approximately 0.01 of the training time required for the XLM-R model. It underscores the potential of linear transformations as a pragmatic alternative to resource-intensive and slower Transformer-based models in real-world applications. The LLMs achieved impressive results that are on par or better, at least by 1%–3%, but with additional hardware requirements and limitations. Overall, this study contributes to understanding cross-lingual sentiment analysis and provides valuable insights into the strengths and limitations of cross-lingual approaches for sentiment analysis.

Reinforced Transformer with Cross-Lingual Distillation for Cross-Lingual Aspect Sentiment Classification

Though great progress has been made in the Aspect-Based Sentiment Analysis(ABSA) task through research, most of the previous work focuses on English-based ABSA problems, and there are few efforts on other languages mainly due to the lack of training data. In this paper, we propose an approach for performing a Cross-Lingual Aspect Sentiment Classification (CLASC) task which leverages the rich resources in one language (source language) for aspect sentiment classification in a under-resourced language (target language). Specifically, we first build a bilingual lexicon for domain-specific training data to translate the aspect category annotated in the source-language corpus and then translate sentences from the source language to the target language via Machine Translation (MT) tools. However, most MT systems are general-purpose, it non-avoidably introduces translation ambiguities which would degrade the performance of CLASC. In this context, we propose a novel approach called Reinforced Transformer with Cross-Lingual Distillation (RTCLD) combined with target-sensitive adversarial learning to minimize the undesirable effects of translation ambiguities in sentence translation. We conduct experiments on different language combinations, treating English as the source language and Chinese, Russian, and Spanish as target languages. The experimental results show that our proposed approach outperforms the state-of-the-art methods on different target languages.

Zero-Shot Learning for Cross-Lingual News Sentiment Classification

In this paper, we address the task of zero-shot cross-lingual news sentiment classification. Given the annotated dataset of positive, neutral, and negative news in Slovene, the aim is to develop a news classification system that assigns the sentiment category not only to Slovene news, but to news in another language without any training data required. Our system is based on the multilingual BERTmodel, while we test different approaches for handling long documents and propose a novel technique for sentiment enrichment of the BERT model as an intermediate training step. With the proposed approach, we achieve state-of-the-art performance on the sentiment analysis task on Slovenian news. We evaluate the zero-shot cross-lingual capabilities of our system on a novel news sentiment test set in Croatian. The results show that the cross-lingual approach also largely outperforms the majority classifier, as well as all settings without sentiment enrichment in pre-training.

Coarse Alignment of Topic and Sentiment: A Unified Model for Cross-Lingual Sentiment Classification.

Cross-lingual sentiment classification (CLSC) aims to leverage rich-labeled resources in the source language to improve prediction models of a resource-scarce domain in the target language. Existing feature representation learning-based approaches try to minimize the difference of latent features between different domains by exact alignment, which is achieved by either one-to-one topic alignment or matrix projection. Exact alignment, however, restricts the representation flexibility and further degrades the model performances on CLSC tasks if the distribution difference between two language domains is large. On the other hand, most previous studies proposed document-level models or ignored sentiment polarities of topics that might lead to insufficient learning of latent features. To solve the abovementioned problems, we propose a coarse alignment mechanism to enhance the model's representation by a group-to-group topic alignment into an aspect-level fine-grained model. First, we propose an unsupervised aspect, opinion, and sentiment unification model (AOS), which trimodels aspects, opinions, and sentiments of reviews from different domains and helps capture more accurate latent feature representation by a coarse alignment mechanism. To further boost AOS, we propose ps-AOS, a partial supervised AOS model, in which labeled source language data help minimize the difference of feature representations between two language domains with the help of logistics regression. Finally, an expectation-maximization framework with Gibbs sampling is then proposed to optimize our model. Extensive experiments on various multilingual product review data sets show that ps-AOS significantly outperforms various kinds of state-of-the-art baselines.

On the Effect of Word Order on Cross-lingual Sentiment Analysis

Current state-of-the-art models for sentiment analysis make use of word order either explicitly by pre-training on a language modeling objective or implicitly by using recurrent neural networks (Rnns) or convolutional networks (Cnns). This is a problem for cross-lingual models that use bilingual embeddings as features, as the difference in word order between source and target languages is not resolved. In this work, we explore reordering as a pre-processing step for sentence-level crosslingual sentiment classification with two language combinations (English-Spanish, English-Catalan). We find that while reordering helps both models, Cnns are more sensitive to local reorderings, while global reordering benefits Rnns.

Cross-Lingual Sentiment Quantification

Sentiment Quantification is the task of estimating the relative frequency of sentiment-related classes—such as ${\sf Positive}$Positive and ${\sf Negative}$Negative—in a set of unlabeled documents. It is an important topic in sentiment analysis, as the study of sentiment-related quantities and trends across a population is often of higher interest than the analysis of individual instances. In this article, we propose a method for cross-lingual sentiment quantification, the task of performing sentiment quantification when training documents are available for a source language $\mathcal {S}$S, but not for the target language $\mathcal {T}$T, for which sentiment quantification needs to be performed. Cross-lingual sentiment quantification (and cross-lingual text quantification in general) has never been discussed before in the literature; we establish baseline results for the binary case by combining state-of-the-art quantification methods with methods capable of generating cross-lingual vectorial representations of the source and target documents involved. Experiments on publicly available datasets for cross-lingual sentiment classification show that the presented method performs cross-lingual sentiment quantification with high accuracy.

Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification

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 1 ) to transfer the knowledge learned from labeled data on a resource-rich source language to low-resource languages where only unlabeled data exist. 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.

Structural Correspondence Learning for Cross-Lingual Sentiment Classification with One-to-Many Mappings

Structural correspondence learning (SCL) is an effective method for cross-lingual sentiment classification. This approach uses unlabeled documents along with a word translation oracle to automatically induce task specific, cross-lingual correspondences. It transfers knowledge through identifying important features, i.e., pivot features. For simplicity, however, it assumes that the word translation oracle maps each pivot feature in source language to exactly only one word in target language. This one-to-one mapping between words in different languages is too strict. Also the context is not considered at all. In this paper, we propose a cross-lingual SCL based on distributed representation of words; it can learn meaningful one-to-many mappings for pivot words using large amounts of monolingual data and a small dictionary. We conduct experiments on NLP&CC 2013 cross-lingual sentiment analysis dataset, employing English as source language, and Chinese as target language. Our method does not rely on the parallel corpora and the experimental results show that our approach is more competitive than the state-of-the-art methods in cross-lingual sentiment classification.

Cross-Lingual Sentiment Classification from English to Arabic using Machine Translation

Cross-lingual sentiment learning is becoming increasingly important due to the multilingual nature of user-generated content on social media and the scarce resources for languages other than English. However, cross-lingual sentiment learning is a challenging task due to the different distribution between translated data and original data and due to the language gap, i.e. each language has its own ways to express sentiments. This work explores the adaptation of English resources for sentiment analysis to a new language, Arabic. The aim is to design a light model for cross-lingual sentiment classification from English to Arabic, without any manual annotation effort which, at the same time, is easy to build and does not require deep linguistic analysis. The ultimate goal is to find an optimal baseline model and to determine the relation between the noise in the translated data and the accuracy of sentiment classification. Different configurations of several factors are investigated including feature representation, feature reduction methods, and the learning algorithms to find the optimal baseline model. Experiments show that a good classification model can be obtained from translated data regardless of the artificial noise added by machine translation. The results also show a significant cost to automation, and thus the best path to future enhancement is through the inclusion of language-specific knowledge and resources.

Cross-lingual sentiment classification: Similarity discovery plus training data adjustment

The performance of cross-lingual sentiment classification is sharply limited by the language gap, which means that each language has its own ways to express sentiments. Many methods have been designed to transmit sentiment information across languages by making use of machine translation, parallel corpora, auxiliary unlabeled samples and other resources. In this paper, a new approach is proposed based on the selection of training data, where labeled samples highly similar to the target language are put into the training set. The refined training samples are used to build up an effective cross-lingual sentiment classifier focusing on the target language. The proposed approach contains two major strategies: the aligned-translation topic model and the semi-supervised training data adjustment. The aligned-translation topic model provides a cross-language representation space in which the semi-supervised training data adjustment procedure attempts to select effective training samples to eliminate the negative influence of the semantic distribution differences between the original and target languages. The experiments show that the proposed approach is feasible for cross-language sentiment classification tasks and provides insight into the semantic relationship between two different languages.

Distributional Correspondence Indexing for Cross-Lingual and Cross-Domain Sentiment Classification.

Domain Adaptation (DA) techniques aim at enabling machine learning methods learn effective classifiers for a "target'' domain when the only available training data belongs to a different "source'' domain. In this paper we present the Distributional Correspondence Indexing (DCI) method for domain adaptation in sentiment classification. DCI derives term representations in a vector space common to both domains where each dimension reflects its distributional correspondence to a pivot, i.e., to a highly predictive term that behaves similarly across domains. Term correspondence is quantified by means of a distributional correspondence function (DCF). We propose a number of efficient DCFs that are motivated by the distributional hypothesis, i.e., the hypothesis according to which terms with similar meaning tend to have similar distributions in text. Experiments show that DCI obtains better performance than current state-of-the-art techniques for cross-lingual and cross-domain sentiment classification. DCI also brings about a significantly reduced computational cost, and requires a smaller amount of human intervention. As a final contribution, we discuss a more challenging formulation of the domain adaptation problem, in which both the cross-domain and cross-lingual dimensions are tackled simultaneously.

Distributional correspondence indexing for cross-lingual and cross-domain sentiment classification

Domain Adaptation (DA) techniques aim at enabling machine learning methods learn effective classifiers for a "target" domain when the only available training data belongs to a different "source" do...

Cross-lingual sentiment classification with stacked autoencoders

Cross-lingual sentiment classification is a popular research topic in natural language processing. The fundamental challenge of cross-lingual learning stems from a lack of overlap between the featu...

Combination of active learning and self-training for cross-lingual sentiment classification with density analysis of unlabelled samples

In recent years, research in sentiment classification has received considerable attention by natural language processing researchers. Annotated sentiment corpora are the most important resources used in sentiment classification. However, since most recent research works in this field have focused on the English language, there are accordingly not enough annotated sentiment resources in other languages. Manual construction of reliable annotated sentiment corpora for a new language is a labour-intensive and time-consuming task. Projection of sentiment corpus from one language into another language is a natural solution used in cross-lingual sentiment classification. Automatic machine translation services are the most commonly tools used to directly project information from one language into another. However, since term distribution across languages may be different due to variations in linguistic terms and writing styles, cross-lingual methods cannot reach the performance of monolingual methods. In this paper, a novel learning model is proposed based on the combination of uncertainty-based active learning and semi-supervised self-training approaches to incorporate unlabelled sentiment documents from the target language in order to improve the performance of cross-lingual methods. Further, in this model, the density measures of unlabelled examples are considered in active learning part in order to avoid outlier selection. The empirical evaluation on book review datasets in three different languages shows that the proposed model can significantly improve the performance of cross-lingual sentiment classification in comparison with other existing and baseline methods.

Cross-lingual sentiment classification using multiple source languages in multi-view semi-supervised learning

Cross-lingual sentiment classification aims to utilize annotated sentiment resources in one language (typically English) for sentiment classification of text documents in another language. Most existing research works rely on automatic machine translation services to directly project information from one language to another. However, due to the existence of differing linguistic terms and writing styles between different languages, translated data cannot cover all vocabularies which exist in the original data. Further, different term distribution between translated data and original data can lead to low performance in cross-lingual sentiment classification. To overcome these problems, we propose a new model which uses labelled data from multiple source languages in a multi-view semi-supervised learning approach so as to incorporate unlabelled data from the target language into the learning process. The proposed model was applied to book review datasets in four different languages. Experiments have shown that our model can effectively improve the cross-lingual sentiment classification performance in comparison with some baseline methods.

Bi-view semi-supervised active learning for cross-lingual sentiment classification

Recently, sentiment classification has received considerable attention within the natural language processing research community. However, since most recent works regarding sentiment classification have been done in the English language, there are accordingly not enough sentiment resources in other languages. Manual construction of reliable sentiment resources is a very difficult and time-consuming task. Cross-lingual sentiment classification aims to utilize annotated sentiment resources in one language (typically English) for sentiment classification of text documents in another language. Most existing research works rely on automatic machine translation services to directly project information from one language to another. However, different term distribution between original and translated text documents and translation errors are two main problems faced in the case of using only machine translation. To overcome these problems, we propose a novel learning model based on active learning and semi-supervised co-training to incorporate unlabelled data from the target language into the learning process in a bi-view framework. This model attempts to enrich training data by adding the most confident automatically-labelled examples, as well as a few of the most informative manually-labelled examples from unlabelled data in an iterative process. Further, in this model, we consider the density of unlabelled data so as to select more representative unlabelled examples in order to avoid outlier selection in active learning. The proposed model was applied to book review datasets in three different languages. Experiments showed that our model can effectively improve the cross-lingual sentiment classification performance and reduce labelling efforts in comparison with some baseline methods.

Bilingual Co-Training for Sentiment Classification of Chinese Product Reviews

The lack of reliable Chinese sentiment resources limits research progress on Chinese sentiment classification. However, there are many freely available English sentiment resources on the Web. This article focuses on the problem of cross-lingual sentiment classification, which leverages only available English resources for Chinese sentiment classification. We first investigate several basic methods (including lexicon-based methods and corpus-based methods) for cross-lingual sentiment classification by simply leveraging machine translation services to eliminate the language gap, and then propose a bilingual co-training approach to make use of both the English view and the Chinese view based on additional unlabeled Chinese data. Experimental results on two test sets show the effectiveness of the proposed approach, which can outperform basic methods and transductive methods.

Heterogeneous Transfer Learning with RBMs

A common approach in machine learning is to use a large amount of labeled data to train a model. Usually this model can then only be used to classify data in the same feature space. However, labeled data is often expensive to obtain. A number of strategies have been developed by the machine learning community in recent years to address this problem, including: semi-supervised learning,domain adaptation,multi-task learning,and self-taught learning. While training data and test may have different distributions, they must remain in the same feature set. Furthermore, all the above methods work in the same feature space. In this paper, we consider an extreme case of transfer learning called heterogeneous transfer learning — where the feature spaces of the source task and the target tasks are disjoint. Previous approaches mostly fall in the multi-view learning category, where co-occurrence data from both feature spaces is required. We generalize the previous work on cross-lingual adaptation and propose a multi-task strategy for the task. We also propose the use of a restricted Boltzmann machine (RBM), a special type of probabilistic graphical models, as an implementation. We present experiments on two tasks: action recognition and cross-lingual sentiment classification.