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

Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 270
Author(s):  
Hanqian Wu ◽  
Zhike Wang ◽  
Feng Qing ◽  
Shoushan Li
Keyword(s):  
General Purpose ◽  
Sentiment Classification ◽  
Training Data ◽  
Target Language ◽  
Source Language ◽  
Domain Specific ◽  
Novel Approach ◽  
The Rich ◽  
Target Languages ◽  
Cross Lingual

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.

scholarly journals Emoji-Powered Representation Learning for Cross-Lingual Sentiment Classification (Extended Abstract)

2020 ◽  
Author(s):  
Zhenpeng Chen ◽  
Sheng Shen ◽  
Ziniu Hu ◽  
Xuan Lu ◽  
Qiaozhu Mei ◽  
...  
Keyword(s):  
Machine Translation ◽  
Representation Learning ◽  
Sentiment Classification ◽  
Target Language ◽  
Learning Method ◽  
Source Language ◽  
Translation Tools ◽  
Target Languages ◽  
Cross Lingual ◽  
Cross Language

Sentiment classification typically relies on a large amount of labeled data. In practice, the availability of labels is highly imbalanced among different languages. To tackle this problem, cross-lingual sentiment classification approaches aim to transfer knowledge learned from one language that has abundant labeled examples (i.e., the source language, usually English) to another language with fewer labels (i.e., the target language). The source and the target languages are usually bridged through off-the-shelf machine translation tools. Through such a channel, cross-language sentiment patterns can be successfully learned from English and transferred into the target languages. This approach, however, often fails to capture sentiment knowledge specific to the target language. In this paper, we employ emojis, which are widely available in many languages, as a new channel to learn both the cross-language and the language-specific sentiment patterns. We propose a novel representation learning method that uses emoji prediction as an instrument to learn respective sentiment-aware representations for each language. The learned representations are then integrated to facilitate cross-lingual sentiment classification.

scholarly journals Exploiting Cross-Lingual Subword Similarities in Low-Resource Document Classification

2020 ◽  
Vol 34 (05) ◽  
pp. 9547-9554
Author(s):  
Mozhi Zhang ◽  
Yoshinari Fujinuma ◽  
Jordan Boyd-Graber
Keyword(s):  
Knowledge Transfer ◽  
Text Classification ◽  
Document Classification ◽  
Training Data ◽  
Target Language ◽  
Source Language ◽  
Low Resource ◽  
Classification Framework ◽  
Related Language ◽  
Cross Lingual

Text classification must sometimes be applied in a low-resource language with no labeled training data. However, training data may be available in a related language. We investigate whether character-level knowledge transfer from a related language helps text classification. We present a cross-lingual document classification framework (caco) that exploits cross-lingual subword similarity by jointly training a character-based embedder and a word-based classifier. The embedder derives vector representations for input words from their written forms, and the classifier makes predictions based on the word vectors. We use a joint character representation for both the source language and the target language, which allows the embedder to generalize knowledge about source language words to target language words with similar forms. We propose a multi-task objective that can further improve the model if additional cross-lingual or monolingual resources are available. Experiments confirm that character-level knowledge transfer is more data-efficient than word-level transfer between related languages.

scholarly journals Monolingual and Cross-Lingual Intent Detection without Training Data in Target Languages

Electronics ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 1412
Author(s):  
Jurgita Kapočiūtė-Dzikienė ◽  
Askars Salimbajevs ◽  
Raivis Skadiņš
Keyword(s):  
Experimental Investigation ◽  
Training Data ◽  
Fine Tuning ◽  
Target Language ◽  
Learning Approach ◽  
Lazy Learning ◽  
Detection Problem ◽  
Target Languages ◽  
Cross Lingual ◽  
Similar Accuracy

Due to recent DNN advancements, many NLP problems can be effectively solved using transformer-based models and supervised data. Unfortunately, such data is not available in some languages. This research is based on assumptions that (1) training data can be obtained by the machine translating it from another language; (2) there are cross-lingual solutions that work without the training data in the target language. Consequently, in this research, we use the English dataset and solve the intent detection problem for five target languages (German, French, Lithuanian, Latvian, and Portuguese). When seeking the most accurate solutions, we investigate BERT-based word and sentence transformers together with eager learning classifiers (CNN, BERT fine-tuning, FFNN) and lazy learning approach (Cosine similarity as the memory-based method). We offer and evaluate several strategies to overcome the data scarcity problem with machine translation, cross-lingual models, and a combination of the previous two. The experimental investigation revealed the robustness of sentence transformers under various cross-lingual conditions. The accuracy equal to ~0.842 is achieved with the English dataset with completely monolingual models is considered our top-line. However, cross-lingual approaches demonstrate similar accuracy levels reaching ~0.831, ~0.829, ~0.853, ~0.831, and ~0.813 on German, French, Lithuanian, Latvian, and Portuguese languages.

scholarly journals Synthetic Treebanking for Cross-Lingual Dependency Parsing

2016 ◽  
Vol 55 ◽  
pp. 209-248 ◽  
Author(s):  
Jörg Tiedemann ◽  
Zeljko Agić
Keyword(s):  
Machine Translation ◽  
Target Language ◽  
Dependency Parsing ◽  
Practical Applications ◽  
Source Language ◽  
Part Of Speech ◽  
Statistical Dependency ◽  
Target Languages ◽  
Cross Lingual ◽  
The Impact

How do we parse the languages for which no treebanks are available? This contribution addresses the cross-lingual viewpoint on statistical dependency parsing, in which we attempt to make use of resource-rich source language treebanks to build and adapt models for the under-resourced target languages. We outline the benefits, and indicate the drawbacks of the current major approaches. We emphasize synthetic treebanking: the automatic creation of target language treebanks by means of annotation projection and machine translation. We present competitive results in cross-lingual dependency parsing using a combination of various techniques that contribute to the overall success of the method. We further include a detailed discussion about the impact of part-of-speech label accuracy on parsing results that provide guidance in practical applications of cross-lingual methods for truly under-resourced languages.

Building a multi-domain comparable corpus using a learning to rank method

2016 ◽  
Vol 22 (4) ◽  
pp. 627-653 ◽  
Author(s):  
RAZIEH RAHIMI ◽  
AZADEH SHAKERY ◽  
JAVID DADASHKARIMI ◽  
MOZHDEH ARIANNEZHAD ◽  
MOSTAFA DEHGHANI ◽  
...  
Keyword(s):  
Learning To Rank ◽  
Training Data ◽  
Target Language ◽  
Document Similarity ◽  
Comparable Corpora ◽  
Linguistic Resources ◽  
Source Document ◽  
Candidate Target ◽  
Target Languages ◽  
Cross Lingual

AbstractComparable corpora are key translation resources for both languages and domains with limited linguistic resources. The existing approaches for building comparable corpora are mostly based on ranking candidate documents in the target language for each source document using a cross-lingual retrieval model. These approaches also exploit other evidence of document similarity, such as proper names and publication dates, to build more reliable alignments. However, the importance of each evidence in the scores of candidate target documents is determined heuristically. In this paper, we employ a learning to rank method for ranking candidate target documents with respect to each source document. The ranking model is constructed by defining each evidence for similarity of bilingual documents as a feature whose weight is learned automatically. Learning feature weights can significantly improve the quality of alignments, because the reliability of features depends on the characteristics of both source and target languages of a comparable corpus. We also propose a method to generate appropriate training data for the task of building comparable corpora. We employed the proposed learning-based approach to build a multi-domain English–Persian comparable corpus which covers twelve different domains obtained from Open Directory Project. Experimental results show that the created alignments have high degrees of comparability. Comparison with existing approaches for building comparable corpora shows that our learning-based approach improves both quality and coverage of alignments.

scholarly journals Bootstrap Domain-Specific Sentiment Classifiers from Unlabeled Corpora

2018 ◽  
Vol 6 ◽  
pp. 269-285 ◽  
Author(s):  
Andrius Mudinas ◽  
Dell Zhang ◽  
Mark Levene
Keyword(s):  
Supervised Learning ◽  
Learning Algorithms ◽  
General Purpose ◽  
Machine Learning Algorithms ◽  
Sentiment Classification ◽  
Two Phase ◽  
Transductive Learning ◽  
Domain Specific ◽  
Sentiment Lexicon ◽  
Supervised Learning Algorithms

There is often the need to perform sentiment classification in a particular domain where no labeled document is available. Although we could make use of a general-purpose off-the-shelf sentiment classifier or a pre-built one for a different domain, the effectiveness would be inferior. In this paper, we explore the possibility of building domain-specific sentiment classifiers with unlabeled documents only. Our investigation indicates that in the word embeddings learned from the unlabeled corpus of a given domain, the distributed word representations (vectors) for opposite sentiments form distinct clusters, though those clusters are not transferable across domains. Exploiting such a clustering structure, we are able to utilize machine learning algorithms to induce a quality domain-specific sentiment lexicon from just a few typical sentiment words (“seeds”). An important finding is that simple linear model based supervised learning algorithms (such as linear SVM) can actually work better than more sophisticated semi-supervised/transductive learning algorithms which represent the state-of-the-art technique for sentiment lexicon induction. The induced lexicon could be applied directly in a lexicon-based method for sentiment classification, but a higher performance could be achieved through a two-phase bootstrapping method which uses the induced lexicon to assign positive/negative sentiment scores to unlabeled documents first, a nd t hen u ses those documents found to have clear sentiment signals as pseudo-labeled examples to train a document sentiment classifier v ia supervised learning algorithms (such as LSTM). On several benchmark datasets for document sentiment classification, our end-to-end pipelined approach which is overall unsupervised (except for a tiny set of seed words) outperforms existing unsupervised approaches and achieves an accuracy comparable to that of fully supervised approaches.

scholarly journals Optimizing Tokenization Choice for Machine Translation across Multiple Target Languages

2017 ◽  
Vol 108 (1) ◽  
pp. 257-269 ◽  
Author(s):  
Nasser Zalmout ◽  
Nizar Habash
Keyword(s):  
Machine Translation ◽  
Performance Enhancement ◽  
Statistical Machine Translation ◽  
Target Language ◽  
Source Language ◽  
Context Variable ◽  
Significant Performance ◽  
Morphologically Rich Languages ◽  
Target Languages ◽  
Language Text

AbstractTokenization is very helpful for Statistical Machine Translation (SMT), especially when translating from morphologically rich languages. Typically, a single tokenization scheme is applied to the entire source-language text and regardless of the target language. In this paper, we evaluate the hypothesis that SMT performance may benefit from different tokenization schemes for different words within the same text, and also for different target languages. We apply this approach to Arabic as a source language, with five target languages of varying morphological complexity: English, French, Spanish, Russian and Chinese. Our results show that different target languages indeed require different source-language schemes; and a context-variable tokenization scheme can outperform a context-constant scheme with a statistically significant performance enhancement of about 1.4 BLEU points.

scholarly journals Enhanced Meta-Learning for Cross-Lingual Named Entity Recognition with Minimal Resources

2020 ◽  
Vol 34 (05) ◽  
pp. 9274-9281
Author(s):  
Qianhui Wu ◽  
Zijia Lin ◽  
Guoxin Wang ◽  
Hui Chen ◽  
Börje F. Karlsson ◽  
...  
Keyword(s):  
Learning Algorithm ◽  
Named Entity Recognition ◽  
Entity Recognition ◽  
Target Language ◽  
Test Case ◽  
Named Entity ◽  
Meta Learning ◽  
Target Languages ◽  
Cross Lingual ◽  
The Given

For languages with no annotated resources, transferring knowledge from rich-resource languages is an effective solution for named entity recognition (NER). While all existing methods directly transfer from source-learned model to a target language, in this paper, we propose to fine-tune the learned model with a few similar examples given a test case, which could benefit the prediction by leveraging the structural and semantic information conveyed in such similar examples. To this end, we present a meta-learning algorithm to find a good model parameter initialization that could fast adapt to the given test case and propose to construct multiple pseudo-NER tasks for meta-training by computing sentence similarities. To further improve the model's generalization ability across different languages, we introduce a masking scheme and augment the loss function with an additional maximum term during meta-training. We conduct extensive experiments on cross-lingual named entity recognition with minimal resources over five target languages. The results show that our approach significantly outperforms existing state-of-the-art methods across the board.

scholarly journals Zero-Shot Learning for Cross-Lingual News Sentiment Classification

2020 ◽  
Vol 10 (17) ◽  
pp. 5993
Author(s):  
Andraž Pelicon ◽  
Marko Pranjić ◽  
Dragana Miljković ◽  
Blaž Škrlj ◽  
Senja Pollak
Keyword(s):  
Classification System ◽  
State Of The Art ◽  
Sentiment Classification ◽  
Training Data ◽  
Test Set ◽  
Novel Technique ◽  
Analysis Task ◽  
Negative News ◽  
Cross Lingual ◽  
News Sentiment

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.

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

2020 ◽  
pp. 016555152096278
Author(s):  
Rouzbeh Ghasemi ◽  
Seyed Arad Ashrafi Asli ◽  
Saeedeh Momtazi
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Training Data ◽  
Target Language ◽  
Low Resource ◽  
Proposed Model ◽  
Significant Difference ◽  
Cross Lingual

With the advent of deep neural models in natural language processing tasks, having a large amount of training data plays an essential role in achieving accurate models. Creating valid training data, however, is a challenging issue in many low-resource languages. This problem results in a significant difference between the accuracy of available natural language processing tools for low-resource languages compared with rich languages. To address this problem in the sentiment analysis task in the Persian language, we propose a cross-lingual deep learning framework to benefit from available training data of English. We deployed cross-lingual embedding to model sentiment analysis as a transfer learning model which transfers a model from a rich-resource language to low-resource ones. Our model is flexible to use any cross-lingual word embedding model and any deep architecture for text classification. Our experiments on English Amazon dataset and Persian Digikala dataset using two different embedding models and four different classification networks show the superiority of the proposed model compared with the state-of-the-art monolingual techniques. Based on our experiment, the performance of Persian sentiment analysis improves 22% in static embedding and 9% in dynamic embedding. Our proposed model is general and language-independent; that is, it can be used for any low-resource language, once a cross-lingual embedding is available for the source–target language pair. Moreover, by benefitting from word-aligned cross-lingual embedding, the only required data for a reliable cross-lingual embedding is a bilingual dictionary that is available between almost all languages and the English language, as a potential source language.

Sign in / Sign up

Export Citation Format

Share Document