Two New Large Corpora for Vietnamese Aspect-based Sentiment Analysis at Sentence Level

2021 ◽  
Vol 20 (4) ◽  
pp. 1-22
Author(s):  
Dang Van Thin ◽  
Ngan Luu-Thuy Nguyen ◽  
Tri Minh Truong ◽  
Lac Si Le ◽  
Duy Tin Vo
Keyword(s):  
Sentiment Analysis ◽  
Language Processing ◽  
Network Architectures ◽  
Low Resource ◽  
The Neural Network ◽  
Sentence Level ◽  
Push Forward ◽  
Polarity Classification ◽  
Learning Architectures ◽  
Single Approach

Aspect-based sentiment analysis has been studied in both research and industrial communities over recent years. For the low-resource languages, the standard benchmark corpora play an important role in the development of methods. In this article, we introduce two benchmark corpora with the largest sizes at sentence-level for two tasks: Aspect Category Detection and Aspect Polarity Classification in Vietnamese. Our corpora are annotated with high inter-annotator agreements for the restaurant and hotel domains. The release of our corpora would push forward the low-resource language processing community. In addition, we deploy and compare the effectiveness of supervised learning methods with a single and multi-task approach based on deep learning architectures. Experimental results on our corpora show that the multi-task approach based on BERT architecture outperforms the neural network architectures and the single approach. Our corpora and source code are published on this footnoted site. 1

scholarly journals Automated Source Code Generation and Auto-Completion Using Deep Learning: Comparing and Discussing Current Language Model-Related Approaches

AI ◽  
2021 ◽  
Vol 2 (1) ◽  
pp. 1-16
Author(s):  
Juan Cruz-Benito ◽  
Sanjay Vishwakarma ◽  
Francisco Martin-Fernandez ◽  
Ismael Faro
Keyword(s):  
Deep Learning ◽  
Learning Community ◽  
Programming Languages ◽  
Language Processing ◽  
Code Generation ◽  
Language Model ◽  
Language Models ◽  
Stochastic Gradient Descent ◽  
Network Architectures ◽  
Learning Architectures

In recent years, the use of deep learning in language models has gained much attention. Some research projects claim that they can generate text that can be interpreted as human writing, enabling new possibilities in many application areas. Among the different areas related to language processing, one of the most notable in applying this type of modeling is programming languages. For years, the machine learning community has been researching this software engineering area, pursuing goals like applying different approaches to auto-complete, generate, fix, or evaluate code programmed by humans. Considering the increasing popularity of the deep learning-enabled language models approach, we found a lack of empirical papers that compare different deep learning architectures to create and use language models based on programming code. This paper compares different neural network architectures like Average Stochastic Gradient Descent (ASGD) Weight-Dropped LSTMs (AWD-LSTMs), AWD-Quasi-Recurrent Neural Networks (QRNNs), and Transformer while using transfer learning and different forms of tokenization to see how they behave in building language models using a Python dataset for code generation and filling mask tasks. Considering the results, we discuss each approach’s different strengths and weaknesses and what gaps we found to evaluate the language models or to apply them in a real programming context.

scholarly journals Pseudotext Injection and Advance Filtering of Low-Resource Corpus for Neural Machine Translation

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Michael Adjeisah ◽  
Guohua Liu ◽  
Douglas Omwenga Nyabuga ◽  
Richard Nuetey Nortey ◽  
Jinling Song
Keyword(s):  
Machine Translation ◽  
Language Processing ◽  
Training Data ◽  
Target Language ◽  
Similarity Metrics ◽  
Mahalanobis Distances ◽  
Parallel Corpora ◽  
Parallel Corpus ◽  
Low Resource ◽  
Sentence Level

Scaling natural language processing (NLP) to low-resourced languages to improve machine translation (MT) performance remains enigmatic. This research contributes to the domain on a low-resource English-Twi translation based on filtered synthetic-parallel corpora. It is often perplexing to learn and understand what a good-quality corpus looks like in low-resource conditions, mainly where the target corpus is the only sample text of the parallel language. To improve the MT performance in such low-resource language pairs, we propose to expand the training data by injecting synthetic-parallel corpus obtained by translating a monolingual corpus from the target language based on bootstrapping with different parameter settings. Furthermore, we performed unsupervised measurements on each sentence pair engaging squared Mahalanobis distances, a filtering technique that predicts sentence parallelism. Additionally, we extensively use three different sentence-level similarity metrics after round-trip translation. Experimental results on a diverse amount of available parallel corpus demonstrate that injecting pseudoparallel corpus and extensive filtering with sentence-level similarity metrics significantly improves the original out-of-the-box MT systems for low-resource language pairs. Compared with existing improvements on the same original framework under the same structure, our approach exhibits tremendous developments in BLEU and TER scores.

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.

scholarly journals Building a New Sentiment Analysis Dataset for Uzbek Language and Creating Baseline Models

Proceedings ◽  
2019 ◽  
Vol 21 (1) ◽  
pp. 37
Author(s):  
Elmurod Kuriyozov ◽  
Sanatbek Matlatipov
Keyword(s):  
Sentiment Analysis ◽  
Language Processing ◽  
Machine Learning Techniques ◽  
Medium Size ◽  
Learning Models ◽  
Important Goal ◽  
Processing Technologies ◽  
Learning Techniques ◽  
Polarity Classification ◽  
Analysis Models

Making natural language processing technologies available for low-resource languages is an important goal to improve the access to technology in their communities of speakers. In this paper, we provide the first annotated corpora for polarity classification for Uzbek language. Our methodology considers collecting a medium-size manually annotated dataset and a larger-size dataset automatically translated from existing resources. Then, we use these datasets to train sentiment analysis models on the Uzbek language, using both traditional machine learning techniques and recent deep learning models.

scholarly journals Sentiment Analysis using Rapid Miner

2019 ◽  
Vol 8 (9S3) ◽  
pp. 1589-1594
Keyword(s):  
Data Mining ◽  
Text Mining ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Quality Information ◽  
Classification Techniques ◽  
Major Task ◽  
Text Document ◽  
Sentence Level ◽  
Day By Day

Now a day the data grows day by day so data mining replaced by big data. Under data mining, Text mining is one of the processes of deriving structured or quality information or data from text document. It helps to business for finding valuable knowledge. Sentiment analysis is one of the applications in text mining. In sentiment analysis, determine the emotional tone under the text. It is the major task of natural language processing. The objective of this paper to categorize the document in sentence level and review level, and classification techniques applied on the dataset (electronic product data). There is an ensemble number of classification techniques applied on the dataset. Then compare each techniques, based on various parameters and find out which one is best. According to that give better suggestions to the company for improving the product.

scholarly journals Ανάλυση συναισθήματος και γνώμης

2018 ◽  
Author(s):  
Αγγελική-Σπυριδούλα Βλαχοστέργιου
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Context Aware ◽  
Sentence Level ◽  
Document Level

Τα τελευταία χρόνια έχει παρατηρηθεί μια αύξηση του αριθμού των προσπαθειών για την αυτόματη αναγνώριση και κατηγοριοποίηση του ανθρωπίνου συναισθήματος χρησιμοποιώντας σήματα φυσιολογίας, σήματα από το πρόσωπο, τη φωνή, καθώς επίσης και προσωπικές ερμηνείες από κείμενα μεγάλων κοινωνικών δεδομένων. Αρκετοί είναι οι τομείς της έρευνας που θα μπορούσαν να επωφεληθούν από αυτά τα συστήματα: διαδραστικά συστήματα διδασκαλίας, τα οποία να επιτρέπουν στους εκπαιδευτικούς να γνωρίζουν το άγχος των φοιτητών, πρόληψη των ατυχημάτων (π.χ. εντοπισμός της κόπωσης του οδηγού), στρατιωτικά ομαδικά καθήκοντα που χαρακτηρίζονται από μεγάλης διάρκειας περιόδους άγχους και πίεσης και εφαρμογές στον τομέα της Υγείας για την έγκαιρη διάγνωση νευροεκφυλιστικών νόσων (π.χ. νόσος του Πάρκινσον), όπου η εκδήλωση των συμπτωμάτων συμβαίνει πολλά χρόνια μετά την έναρξη του νευροεκφυλισμού.Ωστόσο, παρά τις μέχρι τώρα ερευνητικές προσπάθειες, δεν έχει επιτευχθεί ο μακροπρόθεσμος στόχος της δημιουργίας ενός ισχυρού πλαισίου αναγνώρισης του εξεταζόμενου τομέα έρευνας που να βασίζεται στην ανάλυση και στην ερμηνεία του. Δεν υπάρχει καμία αμφιβολία ότι η δημιουργία του συναισθήματος (affect production) επηρεάζεται από το εκάστοτε πλαίσιο που λαμβάνει χώρα τη δεδομένη στιγμή, όπως το έργο στο οποίο υποβάλλεται ο χρήστης, τα άτομα που αλληλεπιδρούν με το χρήστη, η ταυτότητα αλλά και η εκφραστικότητά τους. Η οποιαδήποτε λοιπόν συμπληρωματική μορφή πληροφορίας πλαισίου αναφορικά με τον εξεταζόμενο τομέα έρευνας μας βοηθά ώστε να απαντήσουμε στο ερώτημα: τί είναι πιθανότερο να συμβεί, εκτρέποντας έτσι τον ταξινομητή από τις πιθανότερες/σχετικές κατηγορίες. Χωρίς το πλαίσιο, ακόμη και οι άνθρωποι μπορεί να παρερμηνεύουν τις παρατηρούμενες εκφράσεις του. Έτσι, με την αντιμετώπιση των προκλήσεων υπό το πρίσμα της αναγνώρισης του συναισθήματος υπό συγκεκριμένο πλαίσιο (context-aware affect analysis), δηλαδή με την καλύτερη μελέτη των πληροφοριών πλαισίου, με την ερμηνεία του σε συγκεκριμένους τομείς εφαρμογών, την αναπαράστασή του, τη μοντελοποίησή του, μπορούμε να προσεγγίσουμε καλύτερα την αναγνώριση του συναισθήματος σε πραγματικό χρόνο. Αντίστοιχα, στον τομέα των προσωπικών ερμηνειών από το κείμενο (Sentiment Analysis) αλλά και γενικότερα στον τομέα της Φυσικής Γλώσσας (Natural Language Processing (NLP)) η συνεισφορά του πλαισίου έγκειται στην καλύτερη αναγνώριση, ερμηνεία και επεξεργασία των απόψεων (opinions) και συναισθημάτων (sentiments) σε κείμενα, τα οποία εξετάζονται σε επίπεδο κειμένου (document-level), προτάσεων sentence-level και χαρακτηριστικών (aspect-level) αντίστοιχα. Στην περίπτωση αυτή, λαμβάνονται υπόψιν η σημασιολογία, οι γνωστικές και οι συναισθηματικές πληροφορίες των υποκειμενικών απαντήσεων των ατόμων. Ειδικότερα, στον τομέα αυτό, η συνεισφορά μας έγκειται στην εκπαίδευση ισχυρών αναπαραστάσεις χαρακτηριστικών από μη επισημειωμένα δεδομένα με τη χρήση Νευρωνικών Δικτύων και συγκεκριμένα με τη χρήση Ανταγωνιστικά Παραγωγικών Μοντέλων (GANs), η χρήση των οποίων έχει επιδείξει εντυπωσιακά αποτελέσματα στον τομέα της Όρασης Υπολογιστών. Η πρωτοτυπία της συγκεριμένης μεθόδου έγκειται στον τρόπο υλοποίησης του μοντέλου, στην επιλογή των υπερπαραμετρων, στη χρήση μη επιβλεπόμενης μάθησης και στην πειραματική επικύρωση του προτεινόμενου μοντέλου σε σώματα κειμένου που προέρχονται από διαφορετικές πηγές αναφορικά με το είδος τους και την έκτασή τους.

Deep Learning for Sentiment Analysis

2021 ◽  
pp. 97-132
Author(s):  
Vincent Karas ◽  
Björn W. Schuller
Keyword(s):  
Deep Learning ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Data Augmentation ◽  
Future Research ◽  
Network Architectures ◽  
Business Decisions ◽  
Adversarial Networks ◽  
Current Trends ◽  
Recent Developments

Sentiment analysis is an important area of natural language processing that can help inform business decisions by extracting sentiment information from documents. The purpose of this chapter is to introduce the reader to selected concepts and methods of deep learning and show how deep models can be used to increase performance in sentiment analysis. It discusses the latest advances in the field and covers topics including traditional sentiment analysis approaches, the fundamentals of sentence modelling, popular neural network architectures, autoencoders, attention modelling, transformers, data augmentation methods, the benefits of transfer learning, the potential of adversarial networks, and perspectives on explainable AI. The authors' intent is that through this chapter, the reader can gain an understanding of recent developments in this area as well as current trends and potentials for future research.

scholarly journals BengSentiLex and BengSwearLex: creating lexicons for sentiment analysis and profanity detection in low-resource Bengali language

2021 ◽  
Vol 7 ◽  
pp. e681
Author(s):  
Salim Sazzed
Keyword(s):  
Social Media ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Supervised Machine Learning ◽  
Translation System ◽  
Low Resource ◽  
Part Of Speech ◽  
Sentiment Lexicon ◽  
Cross Lingual ◽  
Bengali Language

Bengali is a low-resource language that lacks tools and resources for various natural language processing (NLP) tasks, such as sentiment analysis or profanity identification. In Bengali, only the translated versions of English sentiment lexicons are available. Moreover, no dictionary exists for detecting profanity in Bengali social media text. This study introduces a Bengali sentiment lexicon, BengSentiLex, and a Bengali swear lexicon, BengSwearLex. For creating BengSentiLex, a cross-lingual methodology is proposed that utilizes a machine translation system, a review corpus, two English sentiment lexicons, pointwise mutual information (PMI), and supervised machine learning (ML) classifiers in various stages. A semi-automatic methodology is presented to develop BengSwearLex that leverages an obscene corpus, word embedding, and part-of-speech (POS) taggers. The performance of BengSentiLex compared with the translated English lexicons in three evaluation datasets. BengSentiLex achieves 5%–50% improvement over the translated lexicons. For identifying profanity, BengSwearLex achieves documentlevel coverage of around 85% in an document-level in the evaluation dataset. The experimental results imply that BengSentiLex and BengSwearLex are effective resources for classifying sentiment and identifying profanity in Bengali social media content, respectively.

scholarly journals Sentiment analysis: a challenge

2018 ◽  
Vol 7 (2.27) ◽  
pp. 291 ◽  
Author(s):  
Ekta Gupta ◽  
Ashok Kumar ◽  
Manish Kumar
Keyword(s):  
Sentiment Analysis ◽  
Language Processing ◽  
Opinion Mining ◽  
Accurate Result ◽  
Product Reviews ◽  
General Process ◽  
Sentence Level ◽  
Complete Procedure ◽  
Future Work ◽  
Online Buying

Sentiment analysis or judgment/thoughts mining is one of the major jobs of NLP (Natural Language Processing). Sentiment analysis has acquired much awareness in recent years. In this paper, our focus is to approach the problem of sentiment polarity assortment, which is one of the elementary problems of sentiment analysis. A general process for sentiment polarity assortment is considered with complete procedure explanation. Data used in this research are online buying product reviews collected from the shopping platform Amazon.com. Experiments for both sentence-level assortment and review-level assortment are executed with guarantee outcomes. Sentiment analysis will help to enhance the business with its performance of giving accurate result .In the end; we also give awareness into our future work on sentiment analysis. From last decade there is no such work has done on sentiment analysis to improve the product quality on the basis of what the customer needs and sometimes it is introduce as opinion mining while the importance in this case is on extraction.  

scholarly journals Survey on Neural Network Architectures with Deep Learning

2020 ◽  
Vol 2 (3) ◽  
pp. 186-194
Author(s):  
Smys S. ◽  
Joy Iong Zong Chen ◽  
Subarna Shakya
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Visual Recognition ◽  
Research Work ◽  
Network Architectures ◽  
Significant Performance ◽  
Recent Trends ◽  
Cost Efficient ◽  
The Cost ◽  
Learning Architectures

In the present research era, machine learning is an important and unavoidable zone where it provides better solutions to various domains. In particular deep learning is one of the cost efficient, effective supervised learning model, which can be applied to various complicated issues. Since deep learning has various illustrative features and it doesn’t depend on any limited learning methods which helps to obtain better solutions. As deep learning has significant performance and advancements it is widely used in various applications like image classification, face recognition, visual recognition, language processing, speech recognition, object detection and various science, business analysis, etc., This survey work mainly provides an insight about deep learning through an intensive analysis of deep learning architectures and its characteristics along with its limitations. Also, this research work analyses recent trends in deep learning through various literatures to explore the present evolution in deep learning models.

Sign in / Sign up

Export Citation Format

Share Document