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.

Statistical Machine Translation with Scarce Resources Using Morpho-syntactic Information

2004 ◽  
Vol 30 (2) ◽  
pp. 181-204 ◽  
Author(s):  
Sonja Nießen ◽  
Hermann Ney
Keyword(s):  
Machine Translation ◽  
Statistical Machine Translation ◽  
Training Data ◽  
Target Language ◽  
Linguistic Knowledge ◽  
Parallel Corpora ◽  
Scarce Resources ◽  
Translation Quality ◽  
Sentence Level ◽  
Statistical Systems

In statistical machine translation, correspondences between the words in the source and the target language are learned from parallel corpora, and often little or no linguistic knowledge is used to structure the underlying models. In particular, existing statistical systems for machine translation often treat different inflected forms of the same lemma as if they were independent of one another. The bilingual training data can be better exploited by explicitly taking into account the interdependencies of related inflected forms. We propose the construction of hierarchical lexicon models on the basis of equivalence classes of words. In addition, we introduce sentence-level restructuring transformations which aim at the assimilation of word order in related sentences. We have systematically investigated the amount of bilingual training data required to maintain an acceptable quality of machine translation. The combination of the suggested methods for improving translation quality in frameworks with scarce resources has been successfully tested: We were able to reduce the amount of bilingual training data to less than 10% of the original corpus, while losing only 1.6% in translation quality. The improvement of the translation results is demonstrated on two German-English corpora taken from the Verbmobil task and the Nespole! task.

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 A brief study of the Autshumato Machine Translation Web Service for South African languages

Literator ◽  
2021 ◽  
Vol 42 (1) ◽  
Author(s):  
Nomsa J. Skosana ◽  
Respect Mlambo
Keyword(s):  
Web Service ◽  
South African ◽  
Machine Translation ◽  
Language Processing ◽  
High Speed ◽  
Training Data ◽  
Parallel Corpora ◽  
African Languages ◽  
Official Languages

The scarcity of adequate resources for South African languages poses a huge challenge for their functional development in specialised fields such as science and technology. The study examines the Autshumato Machine Translation (MT) Web Service, created by the Centre for Text Technology at the North-West University. This software supports both formal and informal translations as a machine-aided human translation tool. We investigate the system in terms of its advantages and limitations and suggest possible solutions for South African languages. The results show that the system is essential as it offers high-speed translation and operates as an open-source platform. It also provides multiple translations from sentences, documents and web pages. Some South African languages were included whilst others were excluded and we find this to be a limitation of the system. We also find that the system was trained with a limited amount of data, and this has an adverse effect on the quality of the output. The study suggests that adding specialised parallel corpora from various contemporary fields for all official languages and involving language experts in the pre-editing of training data can be a major step towards improving the quality of the system’s output. The study also outlines that developers should consider integrating the system with other natural language processing applications. Finally, the initiatives discussed in this study will help to improve this MT system to be a more effective translation tool for all the official languages of South Africa.

Neural machine translation of low-resource languages using SMT phrase pair injection

2020 ◽  
pp. 1-22
Author(s):  
Sukanta Sen ◽  
Mohammed Hasanuzzaman ◽  
Asif Ekbal ◽  
Pushpak Bhattacharyya ◽  
Andy Way
Keyword(s):  
Machine Translation ◽  
Large Scale ◽  
Production Systems ◽  
Statistical Machine Translation ◽  
Training Data ◽  
Original Training ◽  
Neural Machine Translation ◽  
Parallel Corpus ◽  
Low Resource ◽  
Better Than

Abstract Neural machine translation (NMT) has recently shown promising results on publicly available benchmark datasets and is being rapidly adopted in various production systems. However, it requires high-quality large-scale parallel corpus, and it is not always possible to have sufficiently large corpus as it requires time, money, and professionals. Hence, many existing large-scale parallel corpus are limited to the specific languages and domains. In this paper, we propose an effective approach to improve an NMT system in low-resource scenario without using any additional data. Our approach aims at augmenting the original training data by means of parallel phrases extracted from the original training data itself using a statistical machine translation (SMT) system. Our proposed approach is based on the gated recurrent unit (GRU) and transformer networks. We choose the Hindi–English, Hindi–Bengali datasets for Health, Tourism, and Judicial (only for Hindi–English) domains. We train our NMT models for 10 translation directions, each using only 5–23k parallel sentences. Experiments show the improvements in the range of 1.38–15.36 BiLingual Evaluation Understudy points over the baseline systems. Experiments show that transformer models perform better than GRU models in low-resource scenarios. In addition to that, we also find that our proposed method outperforms SMT—which is known to work better than the neural models in low-resource scenarios—for some translation directions. In order to further show the effectiveness of our proposed model, we also employ our approach to another interesting NMT task, for example, old-to-modern English translation, using a tiny parallel corpus of only 2.7K sentences. For this task, we use publicly available old-modern English text which is approximately 1000 years old. Evaluation for this task shows significant improvement over the baseline NMT.

scholarly journals Hindi Chhattisgarhi Machine Translation System Using Statistical Approach

Webology ◽  
2021 ◽  
Vol 18 (Special Issue 02) ◽  
pp. 208-222
Author(s):  
Vikas Pandey ◽  
Dr.M.V. Padmavati ◽  
Dr. Ramesh Kumar
Keyword(s):  
Machine Translation ◽  
Language Processing ◽  
Statistical Approach ◽  
Statistical Machine Translation ◽  
Target Language ◽  
Translation System ◽  
Parallel Corpus ◽  
Machine Translation System ◽  
Unknown Words ◽  
Language Pair

Machine Translation is a subfield of Natural language Processing (NLP) which uses to translate source language to target language. In this paper an attempt has been made to make a Hindi Chhattisgarhi machine translation system which is based on statistical approach. In the state of Chhattisgarh there is a long awaited need for Hindi to Chhattisgarhi machine translation system for converting Hindi into Chhattisgarhi especially for non Chhattisgarhi speaking people. In order to develop Hindi Chhattisgarhi statistical machine translation system an open source software called Moses is used. Moses is a statistical machine translation system and used to automatically train the translation model for Hindi Chhattisgarhi language pair called as parallel corpus. A collection of structured text to study linguistic properties is called corpus. This machine translation system works on parallel corpus of 40,000 Hindi-Chhattisgarhi bilingual sentences. In order to overcome translation problem related to proper noun and unknown words, a transliteration system is also embedded in it. These sentences are extracted from various domains like stories, novels, text books and news papers etc. This system is tested on 1000 sentences to check the grammatical correctness of sentences and it was found that an accuracy of 75% is achieved.

Semantic approach for building generated virtual-parallel corpora from monolingual texts

2019 ◽  
Vol 55 (2) ◽  
pp. 469-490
Author(s):  
Krzysztof Wołk ◽  
Agnieszka Wołk ◽  
Krzysztof Marasek
Keyword(s):  
Machine Translation ◽  
Language Processing ◽  
Research Process ◽  
Levenshtein Distance ◽  
Language Resources ◽  
Semantic Approach ◽  
Parallel Corpora ◽  
Parallel Corpus ◽  
Comparable Corpora ◽  
Translation Systems

Abstract Several natural languages have undergone a great deal of processing, but the problem of limited textual linguistic resources remains. The manual creation of parallel corpora by humans is rather expensive and time consuming, while the language data required for statistical machine translation (SMT) do not exist in adequate quantities for their statistical information to be used to initiate the research process. On the other hand, applying known approaches to build parallel resources from multiple sources, such as comparable or quasi-comparable corpora, is very complicated and provides rather noisy output, which later needs to be further processed and requires in-domain adaptation. To optimize the performance of comparable corpora mining algorithms, it is essential to use a quality parallel corpus for training of a good data classifier. In this research, we have developed a methodology for generating an accurate parallel corpus (Czech-English, Polish-English) from monolingual resources by calculating the compatibility between the results of three machine translation systems. We have created translations of large, single-language resources by applying multiple translation systems and strictly measuring translation compatibility using rules based on the Levenshtein distance. The results produced by this approach were very favorable. The generated corpora successfully improved the quality of SMT systems and seem to be useful for many other natural language processing tasks.

scholarly journals MetaMT, a Meta Learning Method Leveraging Multiple Domain Data for Low Resource Machine Translation

2020 ◽  
Vol 34 (05) ◽  
pp. 8245-8252
Author(s):  
Rumeng Li ◽  
Xun Wang ◽  
Hong Yu
Keyword(s):  
Machine Translation ◽  
Domain Adaptation ◽  
Training Data ◽  
Model Parameters ◽  
Parallel Corpora ◽  
Training Strategy ◽  
Low Resource ◽  
Domain Specific ◽  
Representational Space ◽  
Meta Learning

Neural machine translation (NMT) models have achieved state-of-the-art translation quality with a large quantity of parallel corpora available. However, their performance suffers significantly when it comes to domain-specific translations, in which training data are usually scarce. In this paper, we present a novel NMT model with a new word embedding transition technique for fast domain adaption. We propose to split parameters in the model into two groups: model parameters and meta parameters. The former are used to model the translation while the latter are used to adjust the representational space to generalize the model to different domains. We mimic the domain adaptation of the machine translation model to low-resource domains using multiple translation tasks on different domains. A new training strategy based on meta-learning is developed along with the proposed model to update the model parameters and meta parameters alternately. Experiments on datasets of different domains showed substantial improvements of NMT performances on a limited amount of data.

English-Dogri Translation System using MOSES

2016 ◽  
Vol 1 (1) ◽  
pp. 45-49
Author(s):  
Avinash Singh ◽  
Asmeet Kour ◽  
Shubhnandan S. Jamwal
Keyword(s):  
Natural Language Processing ◽  
Machine Translation ◽  
Language Processing ◽  
Statistical Machine Translation ◽  
Translation System ◽  
Parallel Corpus ◽  
English System ◽  
Machine Translation System ◽  
Translation Machine ◽  
Language Pair

The objective behind this paper is to analyze the English-Dogri parallel corpus translation. Machine translation is the translation from one language into another language. Machine translation is the biggest application of the Natural Language Processing (NLP). Moses is statistical machine translation system allow to train translation models for any language pair. We have developed translation system using Statistical based approach which helps in translating English to Dogri and vice versa. The parallel corpus consists of 98,973 sentences. The system gives accuracy of 80% in translating English to Dogri and the system gives accuracy of 87% in translating Dogri to English system.

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

Analyzing Subword Techniques to Improve English to Sinhala Neural Machine Translation

2021 ◽  
pp. 2050017
Author(s):  
Rashmini Naranpanawa ◽  
Ravinga Perera ◽  
Thilakshi Fonseka ◽  
Uthayasanker Thayasivam
Keyword(s):  
Machine Translation ◽  
State Of The Art ◽  
Statistical Machine Translation ◽  
Translation System ◽  
Rare Word ◽  
Neural Machine Translation ◽  
Parallel Corpus ◽  
Low Resource ◽  
Word Level ◽  
Morphologically Rich Languages

Neural machine translation (NMT) is a remarkable approach which performs much better than the Statistical machine translation (SMT) models when there is an abundance of parallel corpus. However, vanilla NMT is primarily based upon word-level with a fixed vocabulary. Therefore, low resource morphologically rich languages such as Sinhala are mostly affected by the out of vocabulary (OOV) and Rare word problems. Recent advancements in subword techniques have opened up opportunities for low resource communities by enabling open vocabulary translation. In this paper, we extend our recently published state-of-the-art EN-SI translation system using the transformer and explore standard subword techniques on top of it to identify which subword approach has a greater effect on English Sinhala language pair. Our models demonstrate that subword segmentation strategies along with the state-of-the-art NMT can perform remarkably when translating English sentences into a rich morphology language regardless of a large parallel corpus.

Sign in / Sign up

Export Citation Format

Share Document