Corpus-based Machine Translation Research Articles

Transcending Linguistic Boundaries: A Technical Exploration of The Evolution and Future Trajectory of Corpus-Based Machine Translation

This review paper presents a comprehensive examination of the evolution, current state, and future perspectives of machine translation (MT). The field of MT, encompassing the automatic translation of text from one language to another, has undergone significant transformations from rule-based methods to statistical models, and more recently, to neural network-based approaches. By synthesizing current research and technological progress, this paper aims to provide a detailed understanding of the dynamic landscape of machine translation and its future directions. In today's globalized world, language barriers remain a significant obstacle to accessing information. Relying solely on human translators often fails to meet the growing demand for translation services, which is why Machine Translation (MT) tools are becoming increasingly popular. These tools have the potential to address this issue effectively. As a result, research in MT is expanding rapidly, and new paradigms are continually being developed. This paper presents a systematic literature review to identify the most widely used MT systems, their architectures, the quality assessment methods used to evaluate them, and which systems deliver the best results.

Corpus-based Intangible Cultural Heritage Translation Path and Strategy Analysis of Chinese Culture "Going Out"

Intangible cultural heritage translation is regarded as a new subject in the new era of economic construction development, can not only the external publicity of the rich national culture, but also improve our country's cultural propaganda comprehensive level. By studying the corpus-based intangible cultural heritage translation path, the quality and efficiency of cultural translation can be comprehensively improved, and the reliable translation principles and effective strategies of large-scale data can be defined, which can provide effective basis for international cultural publicity in the new era. Therefore, on the basis of understanding the research status of corpus and intangible cultural heritage translation, this paper mainly discusses the corpus-based machine translation system, and then analyzes effective strategies for Chinese culture to "go out" from the perspective of practical development.

Translation Quality Regarding Low-Resource, Custom Machine Translations: A Fine-Grained Comparative Study on Turkish-to-English Statistical and Neural Machine Translation Systems

Corpus-based machine translation (MT) has been the main approach to developing and implementing MT systems in both academia and the industry over the last three decades. In this field, the type and size of the corpus used for training MT engines have presented problems for both statistical MT (SMT) systems as well as neural MT (NMT) systems, being the two dominant corpusbased approaches. Moreover, language pairs such as Turkish-English have been understudied within this framework. This article aims to evaluate the translation quality in Turkish-to-English custom MT systems that have been trained on different corpus sizes and types. Two NMT engines and two SMT engines were trained on the KantanMT platform using two different training corpus types with either only domain-specific cardiology corpus or this corpus plus a mixed-domain corpus. The study conducted both automatic evaluations with metrics including BLEU, F-Measure and TER, as well as a comprehensive human evaluation with metrics including fluency, A/B test, and adequacy. Lastly, the study realized a separate, subjective terminology evaluation in order to investigate how differently MT systems handle terminology, as this is a crucial aspect for specific-domain text types such as cardiology. While the automatic evaluation results suggest the SMT engines to perform better than NMT engines, all human evaluators rated the mixed-domain NMT engine as the highest performing one. However, the terminology evaluation task demonstrated SMT to still be able to perform better and to commit less terminology errors, despite the industry and academia shifting toward NMT engines.

A Domain Specific Parallel Corpus and Enhanced English-Assamese Neural Machine Translation

Machine translation deals with automatic translation from one natural language to another. Neural machine translation is a widely accepted technique of the corpus-based machine translation approach. However, an adequate amount of training data is required, and there is a need for the domain-wise parallel corpus to improve translational performance that shows translational coverages in various domains. In this work, a domain-specific parallel corpus is prepared that includes different domain coverages, namely, Agriculture, Government Office, Judiciary, Social Media, Tourism, COVID-19, Sports, and Literature domains for low-resource English-Assamese pair translation. Moreover, we have tackled data scarcity and word-order divergence problems via data augmentation and prior alignment concept. Also, we have contributed Assamese pre-trained LM, Assamese word-embeddings by utilizing Assamese monolingual data, and a bilingual dictionary-based post-processing step to enhance transformer-based neural machine translation. We have achieved state-of-the-art results for both forward (English-to-Assamese) and backward (Assamese-to-English) directions of translation.

The explanatory power of descriptive translation studies in the machine translation era

ABSTRACT Machine translation (MT) accounts for the largest, and increasingly growing, proportion of translated text produced today, yet the most influential theoretical frameworks developed in translation studies had preceded the contemporary MT era by decades. The question arises as to whether these theories are well-equipped to capture the makeup of today's corpus-based MT. The current article examines and compares the explanatory power of different theoretical frameworks with regard to MT processes and phenomena. The article discusses the incongruences between corpus-based MT algorithms and major paradigms of (human) translation such as natural equivalence, Skopos theory, and poststructuralist approaches. The article then argues that Descriptive Translation Studies (DTS), in its classic formulation introduced and advanced by Gideon Toury, is the theoretical approach that best corresponds to, and is the most useful framework for conceptualizing, the features of corpus-based MT – and, consequently, of an overwhelming proportion of the translation produced today for multilingual communication and understanding.

Low-Resource Multi-Domain Machine Translation for Spanish-Farsi: Neural or Statistical?

An important prerequisite for data-driven Machine Translation (MT) systems is the availability of high-quality training data. Corpus-based MT systems requiring domain specificity additionally require the selection of a large training dataset and application of proper domain adaptation techniques. This paper demonstrates the portability of MT systems to multiple domains under low-resource conditions for the target language, where target-language domain data are not available. We refer to this case as a bilingually low-resource language pair. We compare the performance of an attention-based Neural MT (NMT) system to that of a phrase-based Statistical MT (SMT) system under this condition, training each on parallel corpora consisting of different domains. Experimental results on Spanish-Farsi as a bilingually low-resource language pair show that the SMT paradigm still outperforms that of NMT.

Statistical Machine Translation Customization between Turkish and 11 Languages

Statistical Machine Translation (SMT) has been the dominant corpus-based machine translation (MT) approach in the last twenty years. While SMT has been studied in detail among European languages, it has not been studied sufficiently in language pairs including Turkish as source or target language, and its study has been limited mostly to English ↔ Turkish language pair. This study aims to broaden the perspective on Turkish corpus-based MT studies by training MT engines between Turkish and a wide variety of languages with different features. It surveys customized SMT between Turkish and 11 different languages. Twenty-two SMT engines have been trained in KantanMT with open parallel corpora using Turkish as both source and target language. Three automatic evaluation metrics F-Measure, BLEU, and TER have been used for evaluating MT quality. Due to the variations in the corpus quality and size, highly varying results have been achieved. While Turkish ↔ Catalan engines have had the highest automatic evaluation scores, Turkish ↔ Arabic engines have had the lowest automatic scores. While the quality results are highly varying across languages, we obtain baseline scores for a wide variety of languages coupled with Turkish. These results may provide a reference point for evaluating future MT systems including Turkish.

Research on the Information Processing Model of Source Language of Parallel Corpus

The rapid development of corpus-based machine translation brings opportunities and challenges to the construction of corpus. With the continuous development of information technology, the information processing model of the source language has always been an academic hot topic in natural language processing. In the current machine translation framework, this paper proposes a parallel corpora source language processing model for translation equivalent trees. Firstly, the phrases in the source language and the target language sentence are tagged with parts of speech respectively; Secondly, the word alignment tool is used to align the phrase pairs of the source language and the target language; Syntax analysis is used to parse the source language sentence; Then, a translation equivalence tree is constructed based on the source language syntax tree, target language sentence and word alignment results. Finally, phrase translation pairs are extracted from the translation equivalent tree.

Large aligned treebanks for syntax-based machine translation

We present a collection of parallel treebanks that have been automatically aligned on both the terminal and the non-terminal constituent level for use in syntax-based machine translation. We describe how they were constructed and applied to a syntax- and example-based machine translation system called Parse and Corpus-Based Machine Translation (PaCo-MT). For the language pair Dutch to English, we present non-terminal alignment evaluation scores for a variety of tree alignment approaches. Finally, based on the parallel treebanks created by these approaches, we evaluate the MT system itself and compare the scores with those of Moses, a current state-of-the-art statistical MT system, when trained on the same data.

The Research on the Corpus-Based Machine Translation System

Corpus linguistics has become a study mainstream of language. The research based on corpus is no longer a unique field of computer experts. Developing the machine translation system based on Corpus need to train many high-level talents, which not only are proficient in a number of linguistic theory, with abundant translation and interpretation experience, but also are well versed in computer application software development. Therefore, in this paper, study the corpus-based machine translation methods and analyze the machine translation based on statistics.

Latest trends in hybrid machine translation and its applications

This survey on hybrid machine translation (MT) is motivated by the fact that hybridization techniques have become popular as they attempt to combine the best characteristics of highly advanced pure rule or corpus-based MT approaches. Existing research typically covers either simple or more complex architectures guided by either rule or corpus-based approaches. The goal is to combine the best properties of each type.This survey provides a detailed overview of the modification of the standard rule-based architecture to include statistical knowledge, the introduction of rules in corpus-based approaches, and the hybridization of approaches within this last single category. The principal aim here is to cover the leading research and progress in this field of MT and in several related applications.

A Corpus-based Machine Translation Method of Term Extraction in LSP Texts

To tackle the problems of term extraction in language specific field, this paper proposes a method of coordinating use of corpus and machine translation system in extracting terms in LSP text. A comparable corpus built for this research contains 167 English texts and 229 Chinese texts with around 600,000 English tokens and 900,000 Chinese characters. The corpus is annotated with mega-information and tagged with POS for further use. To get the key word list from the corpus, BFSU PowerConc software is used with the referential corpora of Crown and CLOB for English and TORCH and LCMC for Chinese. A VB program is written to generate the multi-word units, and then GOOGLE translators’ toolkit is used to get translation pairs and SDL trados fuzzy match function is applied to extract lists of multi-word terms and their translations. The results show this method has 70% of translated term pairs scoring 2.0 in a 0~3 grading scale with a 0.5 interval by human graders. The methods can be applied to extract translation term pairs for computer-aided translation of language for specific purpose texts. Also, the by-product comparable corpus, combined with N-gram multiword unit lists, can be used in facilitating trainee translators in translation. The findings underline the significance of combing the use of machine translation method with corpora techniques, and also foresee the necessity of comparable corpora building and sharing and Conc-gram extracting in this field.

Combining Content-Based and URL-Based Heuristics to Harvest Aligned Bitexts from Multilingual Sites with Bitextor

Nowadays, many websites in the Internet are multilingual and may be considered sources of parallel corpora. In this paper we will describe the free/open-source tool Bitextor, created to harvest aligned bitexts from these multilingual websites, which may be used to train corpusbased machine translation systems. This tool uses the work developed in previous approaches with modifications and improvements in order to obtain a tool as adaptable as possible to make it easier to process any kind of websites and work with any pairs of languages. Content-based and URL-based heuristics and algorithms applied to identify and align the parallel web pages in a website will be described and, finally, some results will be presented to show the functionality of the application and set the future work lines for this project.

Automatic extraction of translations from web-based bilingual materials

This paper describes the framework of the StatCan Daily Translation Extraction System (SDTES), a computer system that maps and compares web-based translation texts of Statistics Canada (StatCan) news releases in the StatCan publication The Daily. The goal is to extract translations for translation memory systems, for translation terminology building, for cross-language information retrieval and for corpus-based machine translation systems. Three years of officially published statistical news release texts at http://www.statcan.ca were collected to compose the StatCan Daily data bank. The English and French texts in this collection were roughly aligned using the Gale-Church statistical algorithm. After this, boundary markers of text segments and paragraphs were adjusted and the Gale-Church algorithm was run a second time for a more fine-grained text segment alignment. To detect misaligned areas of texts and to prevent mismatched translation pairs from being selected, key textual and structural properties of the mapped texts were automatically identified and used as anchoring features for comparison and misalignment detection. The proposed method has been tested with web-based bilingual materials from five other Canadian government websites. Results show that the SDTES model is very efficient in extracting translations from published government texts, and very accurate in identifying mismatched translations. With parameters tuned, the text-mapping part can be used to align corpus data collected from official government websites; and the text-comparing component can be applied in prepublication translation quality control and in evaluating the results of statistical machine translation systems.

Correction of errors in a verb modality corpus for machine translation with a machine-learning method

In recent years, various types of tagged corpora have been constructed and much research using tagged corpora has been done. However, tagged corpora contain errors, which impedes the progress of research. Therefore, the correction of errors in corpora is an important research issue. In this study we investigate the correction of such errors, which we call corpus correction. Using machine-learning methods, we applied corpus correction to a verb modality corpus for machine translation. We used the maximum-entropy and decision-list methods as machine-learning methods. We compared several kinds of methods for corpus correction in our experiments, and determined which is most effective by using a statistical test. We obtained several noteworthy findings: (1) Precision was almost the same for both detection and correction, so it is more convenient to do both correction and detection, rather than detection only. (2) In general, the maximum-entropy method worked better than the decision-list method; but the two methods had almost the same precision for the top 50 pieces of extracted data when closed data was used. (3) In terms of precision, the use of closed data was better than the use of open data; however, in terms of the total number of extracted errors, the use of open data was better than the use of closed data. Based on our analysis of these results, we developed a good method for corpus correction. We confirmed the effectiveness of our method by carrying out experiments on machine translation. As corpus-based machine translation continues to be developed, the corpus correction we discuss in this article should prove to be increasingly significant.

Augmented Javanese Speech Levels Machine Translation

This paper presents the development of the hybrid corpus-based machine translation for Javanese language. The system is designed to deal with the complexity of politeness expression and speech levels of Javanese that is considered as a local language with the biggest number of users in Indonesia. Statistical features are embedded to increase the performance of the system. The edit shifting distance is applied due to increase the alignment efficiency. However, improper alignment contributed by recorded impossible pair and insufficient data training is still detected. This paper proposes a new improvement of the developed alignment algorithm based on the impossible pair restriction. Based on experimental results, the new developed algorithm is more accurate (A=93.8%) even though the number of training data is less than the old one (A=87.9%).