Statistical Translation Research Articles

An Analysis of the Factors of Mistranslation in Statistical Machine Translation—Taking Prose Text Translation as Example

An Analysis of the Factors of Mistranslation in Statistical Machine Translation—Taking Prose Text Translation as Example

A Voyage on Neural Machine Translation for Indic Languages

With the invention of deep learning concepts, Machine Translation (MT) migrated towards Neural Machine Translation (NMT) architectures, eventually from Statistical Machine Translation (SMT), which ruled MT for a few decades. Slowly, NMT paved its path into Indian MT research and witnessed many works for various language pairs in this regard. Numerous NMT architectures are floating across the international and national research pool; many claims to be state-of-the-art architectures. Though NMT for Indic languages (ILNMT) is giving better results for majority speaking language pairs, the translation quality is low due to a lack of significant resources. Automated machine translation models are unavailable for some less spoken Indic languages like Kashmiri and Dogri. Hence, there is increasing demand in the research to address the challenges of developing applicable MT models even when minuscule training data is available. Based on the corpus availability, the languages are categorized into High Resource Languages (HRLs), Low Resource Languages (LRLs), and Zero Resource Languages (ZRLs). Many Indic languages are classified into HRLs, LRLs, and ZRLs based on corpus availability. The vision behind this literature survey paper is to make this paper a collective source for all information regarding the predominant ILNMT architectures, the toolkits available for building NMT models, and various pre-trained language models needed by researchers who contribute to the ILNMT research community. In this survey paper, ILNMT architectures for different Indic languages are covered, e.g., Hindi, Tamil (HRLs), Kannada, Marathi (LRLs), Sinhala, and Nepali (ZRLs). There are a few language-specific survey papers on ILNMT, and this is one of the first kinds of survey papers where all the information is gathered under one canopy.

Hyper-parameter optimization in neural-based translation systems: A case study

Abstract Machine translation (MT) is an important use case in natural language processing (NLP) that converts a source language to a target language automatically. Modern intelligent system or artificial intelligence (AI) uses a machine learning approach and the machine has acquired learning ability using datasets. Nowadays, in the MT domain, the neural machine translation (NMT) system has almost replaced the statistical machine translation (SMT) system. The NMT systems use a deep learning framework in their implementation. To achieve higher accuracy during the training of the NMT model, extensive hyper-parameter tuning is required. The paper highlights the significance of hyper-parameter tuning in various machine learning algorithms. And as a case study, in-house experimentation was conducted on a low-resource English–Bangla language pair by designing an NMT system and the significance of various hyper-parameter optimizations was analyzed while evaluating its performance with an automatic metric BLEU. The BLEU scores obtained for the first, second, and third randomly picked test sentences are 4.1, 3.2, and 3.01, respectively.

Corpus Processing of Multi-Word Discourse Markers for Advanced Learners

Aim/Purpose. The most crucial aspects of teaching a foreign language to more advanced learners are building an awareness of discourse modes, how to regulate discourse, and the pragmatic properties of discourse components. However, in different languages, the connections and structure of discourse are ensured by different linguistic means which makes matters complicated for the learner. Background. By uncovering regularities in a foreign language and comparing them with patterns in one’s own tongue, the corpus research method offers the student unique opportunities to acquire linguistic knowledge about discourse markers. This paper reports on an investigation of the functions of multi-word discourse markers. Methodology. In our research, we combine the alignment model of the phrase-based statistical machine translation and manual treatment of the data in order to examine English multi-word discourse markers and their equivalents in Lithuanian and Hebrew translations by researching their changes in translation. After establishing the full list of multi-word discourse markers in our generated parallel corpus, we research how the multi-word discourse markers are treated in translation. Contribution. Creating a parallel research corpus to identify multi-word expressions used as discourse markers, analyzing how they are translated into Lithuanian and Hebrew, and attempting to determine why the translators made the choices add value to corpus-driven research and how to manage discourse. Findings. Our research proves that there is a possible context-based influence guiding the translation to choose a particle or other lexical item integration in Lithuanian or Hebrew translated discourse markers to express the rhetorical domain which could be related to the so-called phenomenon of “over-specification.” Recommendations for Practitioners. The comparative examination of discourse markers provides language instructors and translators with more specific information about the roles of discourse markers. Recommendations for Researchers. Understanding the multifunctionality of discourse markers provides new avenues for discourse marker application in translation research. Impact on Society. The current study may be a useful method to strengthen students’ language awareness and analytic skills and is particularly important for students specializing in English philology or translation. Beyond the empirical research, an extensive parallel data resource has been created to be openly used. Future Research. It should be noted that the observed phenomenon of “over-specification” could be analyzed further in future research.

Pipeline Signed Japanese Translation Using PBSMT and Transformer in a Low-Resource Setting

We propose a novel pipeline method for translating signed Japanese sentences into written Japanese. Sign languages often suppress functional words such as particles, and most words are not morphologically inflected as they are in spoken languages. Our method explicitly compares and contrasts the two languages and divides the translation process into two tasks: first, it translates glosses into lemmatized Japanese words or phrases, followed by complementing particles and conjugating predicates such as verbs, auxiliary verbs, and adjectives. Our method is especially effective when the size of the parallel corpus is very limited and costly to obtain, but there are plenty of monolingual corpora for the target. Specifically, our method first uses phrase-based statistical machine translation (PBSMT) to map sign glosses to corresponding Japanese words or phrases, and then employs a transformer-based neural machine translation (NMT) model trained with a monolingual corpus to refine the output in the first translation. Experimental results show that our pipeline method outperforms direct PBSMT and competitive NMT models with data augmentation, including back-translation and transfer learning in a low-resource setting with a corpus size on the order of 104 words.

Transfer and Triangulation Pivot Translation Approaches for Burmese Dialects

Parallel corpora for the languages of Myanmar (Beik, Burmese, Rakhine) are extremely scarce but a necessary requirement for machine translation R&D. Previous studies have proved that pivoting leads to better translation quality if the bridge language is closely related to the source and target language pair. The baseline study is conducted based on the three major approaches of machine translation; Weighted Finite State Transducer (WFST), Phrase-Based Statistical Machine Translation (PBSMT) and Deep Recurrent Neural Network (Deep-RNN). Based on the baseline results, this paper mainly investigated the pivot language technique for PBSMT with Burmese dialects. We employed two different pivot translation methods: transfer (sentence level) and triangulation (phrase level). We present the experimental results on Dawei-Beik, Beik-Dawei translations and Beik-Rakhine, Rakhine-Beik translation via Burmese. Both the transfer and triangulation approaches outperformed the baseline (direct translation), specifically for the Rakhine-Beik language pair. Moreover, the results of the average BiLingual Evaluation Understudy (BLEU), Character n-gram F-score (chrF), and Word Error Rate (WER) scores of the 10-fold cross-validation experiments proved that the triangulation pivot has significantly better acceleration than the transfer pivot. We plan to release the parallel corpora of Burmese dialects and present several avenues for further research.

Machine translation

Conceived as a scientometric study, this paper searches for comprehending the research status of machine translation on the IEEE database from 1956 to 2019. Documents were analyzed considering a series of measures such as most prominent academic institutions and countries that investigate machine translation, citation, co-authorship, keywords co-occurrence, reference coupling, and textual-based analysis retrieved from the documents’ titles and abstracts. Through VOSviewer software and its tools for data collecting and visualization, machine translation research in the circumscribed database and period of time is focused on three main aspects: machine translation systems, statistical machine translation and English language.

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.

An approach based on deep learning for Indian sign language translation

PurposeAccording to the Indian Sign Language Research and Training Centre (ISLRTC), India has approximately 300 certified human interpreters to help people with hearing loss. This paper aims to address the issue of Indian Sign Language (ISL) sentence recognition and translation into semantically equivalent English text in a signer-independent mode.Design/methodology/approachThis study presents an approach that translates ISL sentences into English text using the MobileNetV2 model and Neural Machine Translation (NMT). The authors have created an ISL corpus from the Brown corpus using ISL grammar rules to perform machine translation. The authors’ approach converts ISL videos of the newly created dataset into ISL gloss sequences using the MobileNetV2 model and the recognized ISL gloss sequence is then fed to a machine translation module that generates an English sentence for each ISL sentence.FindingsAs per the experimental results, pretrained MobileNetV2 model was proven the best-suited model for the recognition of ISL sentences and NMT provided better results than Statistical Machine Translation (SMT) to convert ISL text into English text. The automatic and human evaluation of the proposed approach yielded accuracies of 83.3 and 86.1%, respectively.Research limitations/implicationsIt can be seen that the neural machine translation systems produced translations with repetitions of other translated words, strange translations when the total number of words per sentence is increased and one or more unexpected terms that had no relation to the source text on occasion. The most common type of error is the mistranslation of places, numbers and dates. Although this has little effect on the overall structure of the translated sentence, it indicates that the embedding learned for these few words could be improved.Originality/valueSign language recognition and translation is a crucial step toward improving communication between the deaf and the rest of society. Because of the shortage of human interpreters, an alternative approach is desired to help people achieve smooth communication with the Deaf. To motivate research in this field, the authors generated an ISL corpus of 13,720 sentences and a video dataset of 47,880 ISL videos. As there is no public dataset available for ISl videos incorporating signs released by ISLRTC, the authors created a new video dataset and ISL corpus.

An empirical study on English-Mizo Statistical Machine Translation with Bible Corpus

Machine Translation (MT) is the process of automatically converting the text or speech in one natural language to another language with the help of a machine. This work presents a Bidirectional Statistical Machine Translation (SMT) system of an extremely low resource language pair Mizo-English, built in a low resource setting. A total of 30800 sentences are collected from the English Bible dataset and manually translated to Mizo by a native linguistic expert to generate the English-Mizo parallel dataset. After subjecting to various pre-processing steps, the parallel dataset is used to build our MT system using MOSES tools. Our framework uses different tools, such as GIZA++ for creating the Translation Model (TM) and IRSTLM to determine the probability of the target model. The quality of our MT system is evaluated using two automatic evaluation metrics: BLEU and METEOR. Our MT systems are also manually evaluated using two parameters: adequacy and fluency.

Analysis on the Recent Trends in Machine Translation

Machine translation is to translate one language into another language, which has undergone a great evolution. The model of machine translation has been continuously improved, aiming to make the translation effect closer to the artificial translation. This article briefly summarizes the development history of machine translation, and introduces the main models of each stage of development. The initial machine translation mode is the Rule Based Machine Translation (RBMT) and Statistical Machine Translation (SMT). Recent mainstream translation approach enables Neural Machine Translation (NMT). It includes the input and the output, attention mechanism, and BLEU evaluation method. On this basis, there are also many expansion and innovation models, such as GPKD and other models to improve the evaluation effect. In general, machine translation can replace a part of human translation. However, it cannot completely replace human beings, because of the different human thinking and machine logic. People and machines have to cooperate with each other to improve the common efficiency.

Progress in Machine Translation

After more than 70 years of evolution, great achievements have been made in machine translation. Especially in recent years, translation quality has been greatly improved with the emergence of neural machine translation (NMT). In this article, we first review the history of machine translation from rule-based machine translation to example-based machine translation and statistical machine translation. We then introduce NMT in more detail, including the basic framework and the current dominant framework, Transformer, as well as multilingual translation models to deal with the data sparseness problem. In addition, we introduce cutting-edge simultaneous translation methods that achieve a balance between translation quality and latency. We then describe various products and applications of machine translation. At the end of this article, we briefly discuss challenges and future research directions in this field.

A Machine Translation System from Indian Sign Language to English Text

Sign language recognition and translation is a crucial step towards improving communication between the deaf and the rest of the society. According to the Indian Sign Language Research and Training Centre (ISLRTC), India has around 300 certified human interpreters. With such a shortage of human interpreters, an alternative service is desired that helps people to achieve smooth communicate with deaf. In this study, an approach is presented that translates ISL sentences in English text using MobileNetV2 model and neural machine translation (NMT). The system features ISL corpus created from Brown corpus using ISL grammar rules. The approach converts the ISL videos into ISL gloss sequence using MobileNetV2 model and recognised ISL gloss sequence is then fed to machine translation module. MobileNetV2 was proven best-suited model for recognition of ISL sentences and NMT gives better result than statistical machine translation (SMT) to convert ISL gloss sequence into English text. The automatic and human evaluation of the proposed approach gives 83.3% and 86.1% accuracy, respectively.

MULTIMODAL SPEECH RECOGNITION BASED ON AUDIO AND TEXT DATA

Systems of machine translation of texts from one language to another simulate the work of a human translator. Their performance depends on the ability to understand the grammar rules of the language. In translation, the basic units are not individual words, but word combinations or phraseological units that express different concepts. Only by using them, more complex ideas can be expressed through the translated text. The main feature of machine translation is different length for input and output. The ability to work with different lengths of input and output provides us with the approach of recurrent neural networks. A recurrent neural network (RNN) is a class of artificial neural network that has connections between nodes. In this case, a connection refers to a connection from a more distant node to a less distant node. The presence of connections allows the RNN to remember and reproduce the entire sequence of reactions to one stimulus. From the point of view of programming, such networks are analogous to cyclic execution, and from the point of view of the system, such networks are equivalent to a state machine. RNNs are commonly used to process word sequences in natural language processing. Usually, a hidden Markov model (HMM) and an N-program language model are used to process a sequence of words. Deep learning has completely changed the approach to machine translation. Researchers in the deep learning field has created simple solutions based on machine learning that outperform the best expert systems. In this paper was reviewed the main features of machine translation based on recurrent neural networks. The advantages of systems based on RNN using the sequence-to-sequence model against statistical translation systems are also highlighted in the article. Two machine translation systems based on the sequence-to-sequence model were constructed using Keras and PyTorch machine learning libraries. Based on the obtained results, libraries analysis was done, and their performance comparison.

Challenges of Using Character Level Statistical Machine Translation for Normalizing Old Estonian Texts

This paper reports on experiments of normalizing the 19th century Estonian parish court records. Converting the historical texts from old to contemporary spelling system, also known as normalizing, can be challenging in itself due to the fact that there was no single orthographic standard or if there even was, often the rules were not strictly followed, so there was a lot of variation in the texts. This paper also concentrates on the more specific issues related to Estonian as a morphologically rich language and presents the initial results of applying the character level statistical machine translation normalization on the parish court records from the 19th century. Morphological richness and the peculiarities of the old orthography can create the problem of ambiguity, which we attempted to solve using word bigrams instead of single words for training. Also, as the annotated training data is scarce and we assumed that more of it helps us obtain better results, we tested the idea to create the artificial additional training data, the so-called silver standard. The old texts which’s spellings were closest to modern Estonian were converted to the old spelling system, which is much simpler than the reverse process, and after that added to the training set.

Machine Translation for Low-Resource English-Mizo Pair Encountering Tonal Words

Machine translation is one of the most powerful natural language processing applications for preserving and upgrading low-resource language. Mizo language is considered as low-resource since there is limited availability of resources. Therefore, it is a challenging task for English-Mizo language pair translation. Moreover, Mizo is a tonal language, where a word can express different meanings depending on a variety of tones. There are four variations of tones, namely high, low, rising, and falling. A tone marker is used to represent each of the tones, which is added to the vowels to indicate tone variation. Addressing tonal words in machine translation for such a low-resource pair is another challenging issue. In this paper, the English-Mizo corpus is developed where parallel sentences having tonal words are incorporated. The different machine translation models are explored based on statistical machine translation and neural machine translation for the baseline systems. Furthermore, the proposed approach attempts to augment the train data by expanding parallel data having tonal words and achieves state-of-the-art results for both forward

Strategies and tactics in simultaneous translation

The role and characteristics of simultaneous translation (ST) in the general system of translation are very wide, and deeper knowledge and skills are required from the simultaneous translator. The translator uses a simultaneous interpretation of different types of interpretation, in particular, semantic translation from serial translation and different forms and methods. The translation is also a unique bridge that connects these cultures. Whether it is a written translation or an oral translation, to a certain degree it creates an exchange and acquaintance of cultures. Every language reflects the worldview, psyche, and identity of that nation. It gives a heavier task for the translator when performing the translation. Today, simultaneous translation is widely used in meetings of heads of state and international conferences. It is natural that the main topic of such simultaneous translation processes is about politics and the political environment in the neighboring and international arena. In carrying out political translation, an experienced translator always takes into account the hidden ambiguity in the speaker’s speech. This is because, in the political context of a country, a word that has a positive meaning often has a negative meaning when it is simultaneously translated into another language. It is no coincidence that "Politics is an art." After all, various political metaphors and euphemisms are often used in politics. Therefore, on the one hand, in the process of simultaneous translation, the translator works with traditional phrases, the practical, auxiliary essence of which is clear to him. On the other hand, he works with the message the politician is sending and therefore has to clearly understand to whom it is actually addressed. A knowledgeable interpreter of the political context and subtleties of diplomatic language allows the translator to clearly convey all the emphasized aspects of the message and, if necessary, to add that emotional-expressive tone to the text. This article analyses the presentation of political vocabulary in the Arabic-Uzbek combination of simultaneous translation, the Arabic units of address used in the process of simultaneous translation on a political topic for heads of state and officials in Arab states through various examples and evidence. Simultaneous translation, strategy, the semantic-stylistic structure of communication, dynamic, statistical, waiting strategy, and serial translation.

Traduction d’unités polylexicales du portugais en français par MT@EC et eTranslation

Translation of Multi-Word Units from Portuguese into French by MT@EC and eTranslation
 This paper aims to determine the extent to which the shift from statistical machine translation (SMT) to neural machine translation (NMT) improved the performance of European Union machine translation systems between 2015 and 2021 in terms of multi-word unit translation and domain coverage. To do so, we chose to test these systems on machine translation into French of multi-word units expressing quantitative and qualitative progression in Portuguese from Portugal. These units consist of the 2-gram ‘cada vez’ and a comparative adjective or adverb (cada vez COMP), and their word-for-word translation into French is not idiomatic (*chaque fois COMP). The most frequent translation into French is ‘de COMP en COMP’. This implies that these multi-word units must be translated ‘en bloc’, but their identification is not straightforward. On the one hand, COMP is not fixed and may include one (mais / plus, menos / moins, maior / plus grand, menor / plus petit, melhor / meilleur – mieux, pior / pire – plus mal) or several words (mais or menos N, ADJ, ADV). On the other hand, the 2-gram ‘cada vez’ can be part of other multi-word units expressing iteration (de cada vez (que)/(à) chaque fois (que)), or ‘dropper’ ([a certain quantity] de cada vez/ à la fois), This raises the challenge of ambiguity, well known to biotranslators and still often problematic for NMT. Moreover, units expressing quantitative or qualitative progression may raise other translation challenges when they are coordinate (with or without repetition of the 2-gram ‘cada vez’), when they are split (cada vez (…) COMP), or when they combine with verbs or nouns to form extended translation units whose translation into French can result in a more concise solution we refer to as ‘lexicalisation’. We established a biotranslation model based on a manually aligned French-Portuguese parallel literary corpus and online searchable French-Portuguese aligned corpora (translation memories). We selected a sample of occurrences of these multi-word units including several translation challenges. These occurrences were selected from a Portuguese journalistic corpus. They belong therefore to general language, whereas the EU's translation memories cover the domains dealt with by its institutions, which represents an additional challenge, considering the critical importance of domain coverage in the data to NMT performance quality. The selected occurrences were translated into French by the EU SMT system in 2015 (MT@EC) and 2019 (eTranslation Legacy) and by eTranslation (the EU NMT system) in 2019 and 2021. Firstly, MT output was analysed according to two general criteria: ‘non- literality’, that is translation into French without ‘chaque’, and acceptability from a semantic point of view, that is MT output without any false meaning, opposite meaning or nonsense. Then we looked at specific challenges, some of which could lead to original solutions, worthy of a professional human translator, such as lexicalisation, change of grammatical category or ‘recategorisation’ and ‘naturalisation’, that is phraseological or syntactic rearrangement that makes the target text more idiomatic. The results show that MT is improving, especially according to the criterion of non-literality. Original solutions are still rare, but they are diversifying in NMT output. Nevertheless, NMT remains imperfect, not least because of the inherent ambiguity of natural languages and the inevitable gaps in the data on which these systems are based. The results also demonstrate the importance of human intervention in the maintenance of the systems learning automatically, since the quality of SMT system’s output decreases between 2015 and 2019, when all efforts were focused on improving EU NMT system. Finally, results reveal the dangers of using English as a pivot language when translating from one Romance language into another, and the need to train future translators in NMT and post-editing.

Unsupervised SMT: an analysis of Indic languages and a low resource language

ABSTRACT The rapid globalisation in language technology and the Internet’s fast expansion have brought nations and their cultures close together, and the demand for inter-language interactions has risen enormously. However, in many low-resource languages (LRL) pairings and areas, Machine Translation (MT) is still not viable because of a lack of parallel data. The challenge of MT is still unsolved. Recent studies employing monolingual datasets have shown excellent outcomes in Phrase-based Statistical MT (PBSMT) and Neural MT (NMT) systems. However, earlier researchers have demonstrated that unsupervised Statistical MT surpasses unsupervised NMT, especially for different language pairings. The study unveils the compendium of ten unsupervised SMT systems translation tasks utilizing a monolingual dataset from the Dravidian and Indo-Aryan language families; and a low-resource endangered language. The machine-translated experimental outcomes examined the system using different tokenizers and investigated them for various language pairs using different evaluation metrics for various iterations. The statistical significance of test results has been computed for each evaluation metric to check the true system quality of the translation tasks.

Multilingual Machine Translation System Based on Decoder Recurrent Neural Network

In order to solve the problem that traditional machine translation cannot meet users’ needs due to its slow translation speed, an in-depth study on English translation model based on neural network was proposed. Firstly, three methods of model frame design, translation system design, and training frame design are studied. In order to improve the effectiveness and stability of the English translation model of recursive neural network, a model of English-Chinese machine translation system is designed. The system uses a knowledge-based context vector to map English and Chinese words, and uses a codec recursive neural network to achieve the results. After experiments and researches, the neural network can also efficiently deal with the long-distance reordering problem of multilanguage machine translation, which is difficult for statistical machine translation to deal with effectively. The neural network has opened a broad field of vision for machine translation research.