Phrase-based Statistical Machine Translation Research Articles

Machine translation literacy in the legal translation context: a SWOT analysis perspective

ABSTRACT In the past couple of decades, machine translation (MT), whether phrase-based statistical or neural MT, has made considerable progress and has become increasingly common in specialised translation workflows. More studies on MT in legal contexts have been conducted in the past several years, and MT has been and continues to be used in international and supranational institutions that rely on legal translation and whose voluminous collections of translated text have been used to train contemporary systems. The time is ripe for a synthesis of developments in the area that may reinforce our understanding of what we might expect from MT from the perspective of legal translators. This systematic review of legal translation and MT studies teases out potential strengths/weaknesses of MT and opportunities/threats of using it from a legal translator perspective, focusing on lexical and morphosyntactic challenges that may set legal translation apart from other specialised translation areas. A SWOT analysis from this perspective may offer value as a pedagogical framework for fostering domain-specific MT literacy in the legal translation classroom. Students will develop an understanding of what might reasonably be expected from MT in legal translation contexts, while reinforcing their understanding of legal translation challenges.

Malayalam Natural Language Processing: Challenges in Building a Phrase-Based Statistical Machine Translation System

Statistical Machine Translation (SMT) is a preferred Machine Translation approach to convert the text in a specific language into another by automatically learning translations using a parallel corpus. SMT has been successful in producing quality translations in many foreign languages, but there are only a few works attempted in South Indian languages. The article discusses on experiments conducted with SMT for Malayalam language and analyzes how the methods defined for SMT in foreign languages affect a Dravidian language, Malayalam. The baseline SMT model does not work for Malayalam due to its unique characteristics like agglutinative nature and morphological richness. Hence, the challenge is to identify where precisely the SMT model has to be modified such that it adapts the challenges of the language peculiarity into the baseline model and give better translations for English to Malayalam translation. The alignments between English and Malayalam sentence pairs, subjected to the training process in SMT, plays a crucial role in producing quality output translation. Therefore, this work focuses on improving the translation model of SMT by refining the alignments between English–Malayalam sentence pairs. The phrase alignment algorithms align the verb and noun phrases in the sentence pairs and develop a new set of alignments for the English–Malayalam sentence pairs. These alignment sets refine the alignments formed from Giza++ produced as a result of EM training algorithm. The improved Phrase-Based SMT model trained using these refined alignments resulted in better translation quality, as indicated by the AER and BLUE scores.

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.

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.

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.

Improving Machine Translation Quality with Denoising Autoencoder and Pre-Ordering

The problems in machine translation are related to the characteristics of a family of languages, especially syntactic divergences between languages. In the translation task, having both source and target languages in the same language family is a luxury that cannot be relied upon. The trained models for the task must overcome such differences either through manual augmentations or automatically inferred capacity built into the model design. In this work, we investigated the impact of multiple methods of differing word orders during translation and further experimented in assimilating the source languages syntax to the target word order using pre-ordering. We focused on the field of extremely low-resource scenarios. We also conducted experiments on practical data augmentation techniques that support the reordering capacity of the models through varying the target objectives, adding the secondary goal of removing noises or reordering broken input sequences. In particular, we propose methods to improve translat on quality with the denoising autoencoder in Neural Machine Translation (NMT) and pre-ordering method in Phrase-based Statistical Machine Translation (PBSMT). The experiments with a number of English-Vietnamese pairs show the improvement in BLEU scores as compared to both the NMT and SMT systems.

An empirical evaluation of phrase-based statistical machine translation for Indonesia slang-word translator

<span>The use of slang (non-standard language), especially in social media, is increasing. It causes reducing the level of understanding when communicating because not everyone understands slang (non-standard language). The purpose of this work is to develop a slang-word translator. The other objective is to find the minimum number of sentences and </span><span>BiLingual Evaluation Understudy</span><span> (BLEU) score used as a benchmark to determine that the translation is understandable. The approach used in this project is a Phrase-based statistical machine translation (PBSMT) approach, suitable for low resource language, with a dataset of 100,000 sentences taken from the comments column of several online political news portals. The comments are then manually translated to produce a parallel corpus of non-standard language-standard language. The sample sentences are taken from the dataset then distributed using questionnaires to obtain the human understanding level regarding the translation result. The result of the implementation is a BLEU score of 64 and the minimum number of sentences to have an understandable machine translation is 500. The conclusion drawn from the distributed questionnaires is that humans can understand the sentences produced by the translation machine.</span>

Low Resource Neural Machine Translation: Assamese to/from Other Indo-Aryan (Indic) Languages

Machine translation (MT) systems have been built using numerous different techniques for bridging the language barriers. These techniques are broadly categorized into approaches like Statistical Machine Translation (SMT) and Neural Machine Translation (NMT). End-to-end NMT systems significantly outperform SMT in translation quality on many language pairs, especially those with the adequate parallel corpus. We report comparative experiments on baseline MT systems for Assamese to other Indo-Aryan languages (in both translation directions) using the traditional Phrase-Based SMT as well as some more successful NMT architectures, namely basic sequence-to-sequence model with attention, Transformer, and finetuned Transformer. The results are evaluated using the most prominent and popular standard automatic metric BLEU (BiLingual Evaluation Understudy), as well as other well-known metrics for exploring the performance of different baseline MT systems, since this is the first such work involving Assamese. The evaluation scores are compared for SMT and NMT models for the effectiveness of bi-directional language pairs involving Assamese and other Indo-Aryan languages (Bangla, Gujarati, Hindi, Marathi, Odia, Sinhalese, and Urdu). The highest BLEU scores obtained are for Assamese to Sinhalese for SMT (35.63) and the Assamese to Bangla for NMT systems (seq2seq is 50.92, Transformer is 50.01, and finetuned Transformer is 50.19). We also try to relate the results with the language characteristics, distances, family trees, domains, data sizes, and sentence lengths. We find that the effect of the domain is the most important factor affecting the results for the given data domains and sizes. We compare our results with the only existing MT system for Assamese (Bing Translator) and also with pairs involving Hindi.

A Critique of Statistical Machine Translation

Phrase-Based Statistical Machine Translation (PB-SMT) is clearly the leading paradigm in the field today. Nevertheless—and this may come as some surprise to the PB-SMT community—most translators and, somewhat more surprisingly perhaps, many experienced MT protagonists find the basic model extremely difficult to understand. The main aim of this paper, therefore, is to discuss why this might be the case. Our basic thesis is that proponents of PB-SMT do not seek to address any community other than their own, for they do not feel any need to do so. We demonstrate that this was not always the case; on the contrary, when statistical models of trans-lation were first presented, the language used to describe how such a model might work was very conciliatory, and inclusive. Over the next five years, things changed considerably; once SMT achieved dominance particularly over the rule-based paradigm, it had established a position where it did not need to bring along the rest of the MT community with it, and in our view, this has largely pertained to this day. Having discussed these issues, we discuss three additional issues: the role of automatic MT evaluation metrics when describing PB-SMT systems; the recent syntactic embellishments of PB-SMT, noting especially that most of these contributions have come from researchers who have prior experience in fields other than statistical models of translation; and the relationship between PB-SMT and other models of translation, suggesting that there are many gains to be had if the SMT community were to open up more to the other MT paradigms.

Empirical Analysis of Phrase-Based Statistical Machine Translation System for English to Hindi Language

Hindi is the national language of India. However, most of the Government records, resolutions, news, etc. are documented in English which remote villagers may not understand. This fact motivates to develop an automatic language translation system from English to Hindi. Machine translation is the process of translating a text in one natural language into another natural language using computer system. Grammatical structure of Hindi language is very much complex than English language. The structural difference between English and Hindi language makes it difficult to achieve good quality translation results. In this paper, phrase-based statistical machine translation approach (PBSMT) is used for translation. Translation, reordering and language model are main working components of a PBSMT system. This paper evaluates the impact of various combinations of these PBSMT system parameters on automated English to Hindi language translation quality. Freely available n-gram-based BLEU metric and TER metric are used for evaluating the results.

Minang and Indonesian Pharase-Based Statistical Machine Translation

This research focuses on making a phrase based statistical machine translation for Minang – Indonesian language as well as seeing how well the machine translation results. The source of training and test data in the form of parallel corpus and monolingual corpus that taken from Minang Wikipedia language and Indonesian news website. Two test case scenario were tested in this research that based on the language model and translation model. To see how well the translation will be seen by using Bilingual Evaluation Understudy (BLEU). The result showed that the testing for the first scenario have a significant impact compare to the second scenario in terms of translation. The lack of corpus resources is a problem in building phrase-based statistical machine translation.

Comparing Statistical and Neural Machine Translation Performance on Hindi-To-Tamil and English-To-Tamil

Phrase-based statistical machine translation (PB-SMT) has been the dominant paradigm in machine translation (MT) research for more than two decades. Deep neural MT models have been producing state-of-the-art performance across many translation tasks for four to five years. To put it another way, neural MT (NMT) took the place of PB-SMT a few years back and currently represents the state-of-the-art in MT research. Translation to or from under-resourced languages has been historically seen as a challenging task. Despite producing state-of-the-art results in many translation tasks, NMT still poses many problems such as performing poorly for many low-resource language pairs mainly because of its learning task’s data-demanding nature. MT researchers have been trying to address this problem via various techniques, e.g., exploiting source- and/or target-side monolingual data for training, augmenting bilingual training data, and transfer learning. Despite some success, none of the present-day benchmarks have entirely overcome the problem of translation in low-resource scenarios for many languages. In this work, we investigate the performance of PB-SMT and NMT on two rarely tested under-resourced language pairs, English-To-Tamil and Hindi-To-Tamil, taking a specialised data domain into consideration. This paper demonstrates our findings and presents results showing the rankings of our MT systems produced via a social media-based human evaluation scheme.

Evaluation of English–Slovak Neural and Statistical Machine Translation

This study is focused on the comparison of phrase-based statistical machine translation (SMT) systems and neural machine translation (NMT) systems using automatic metrics for translation quality evaluation for the language pair of English and Slovak. As the statistical approach is the predecessor of neural machine translation, it was assumed that the neural network approach would generate results with a better quality. An experiment was performed using residuals to compare the scores of automatic metrics of the accuracy (BLEU_n) of the statistical machine translation with those of the neural machine translation. The results showed that the assumption of better neural machine translation quality regardless of the system used was confirmed. There were statistically significant differences between the SMT and NMT in favor of the NMT based on all BLEU_n scores. The neural machine translation achieved a better quality of translation of journalistic texts from English into Slovak, regardless of if it was a system trained on general texts, such as Google Translate, or specific ones, such as the European Commission’s (EC’s) tool, which was trained on a specific-domain.

A novel model based on Sequential Adaptive Memory for English–Hindi Translation

Machine-based language translation has been certainly picking up. Still, machines lag behind the cognitive powers of human beings. Neural Machine Translation (NMT) methods require huge datasets and computational power for high-quality translation. A novel Sequential Adaptive Memory (SAM) cognitive model-based machine translation system for English to Hindi translation, was proposed. This model is an augmented version of the Cortical Learning Algorithm (CLA). The SAM is based on the architecture of the neocortex region of the brain, where speech and language comprehension and production take place. The proposed model is capable of learning with smaller datasets. This model employs the sequence to sequence learning approach, which provides better quality translation. It enables the creation of word pairs, dictionaries, and rules for translation. The results of the proposed approach are compared with the traditional phrase-based SMT approach as well as with the state-of-the-art NMT approach. The results are comparable with the results of the conventional approaches. We illustrate that the limitations of the approaches are won over by the proposed SAM approach. It is observed that SAM is capable of exhibiting satisfactory quality translation for low resource languages as well.

Neural Machine Translation With Explicit Phrase Alignment

While neural machine translation has achieved state-of-the-art translation performance, it is unable to capture the alignment between the input and output during the translation process. The lack of alignment in neural machine translation models leads to three problems: it is hard to (1) interpret the translation process, (2) impose lexical constraints, and (3) impose structural constraints. These problems not only increase the difficulty of designing new architectures for neural machine translation, but also limit its applications in practice. To alleviate these problems, we propose to introduce explicit phrase alignment into the translation process of arbitrary neural machine translation models. The key idea is to build a search space similar to that of phrase-based statistical machine translation for neural machine translation where phrase alignment is readily available. We design a new decoding algorithm that can easily impose lexical and structural constraints. Experiments show that our approach makes the translation process of neural machine translation more interpretable without sacrificing translation quality. In addition, our approach achieves significant improvements in lexically and structurally constrained translation tasks.

A roadmap to neural automatic post-editing: an empirical approach

In a translation workflow, machine translation (MT) is almost always followed by a human post-editing step, where the raw MT output is corrected to meet required quality standards. To reduce the number of errors human translators need to correct, automatic post-editing (APE) methods have been developed and deployed in such workflows. With the advances in deep learning, neural APE (NPE) systems have outranked more traditional, statistical, ones. However, the plethora of options, variables and settings, as well as the relation between NPE performance and train/test data makes it difficult to select the most suitable approach for a given use case. In this article, we systematically analyse these different parameters with respect to NPE performance. We build an NPE “roadmap” to trace the different decision points and train a set of systems selecting different options through the roadmap. We also propose a novel approach for APE with data augmentation. We then analyse the performance of 15 of these systems and identify the best ones. In fact, the best systems are the ones that follow the newly-proposed method. The work presented in this article follows from a collaborative project between Microsoft and the ADAPT centre. The data provided by Microsoft originates from phrase-based statistical MT (PBSMT) systems employed in production. All tested NPE systems significantly increase the translation quality, proving the effectiveness of neural post-editing in the context of a commercial translation workflow that leverages PBSMT.

Analysing terminology translation errors in statistical and neural machine translation

Terminology translation plays a critical role in domain-specific machine translation (MT). Phrase-based statistical MT (PB-SMT) has been the dominant approach to MT for the past 30 years, both in academia and industry. Neural MT (NMT), an end-to-end learning approach to MT, is steadily taking the place of PB-SMT. In this paper, we conduct comparative qualitative evaluation and comprehensive error analysis on terminology translation in PB-SMT and NMT in two translation directions: English-to-Hindi and Hindi-to-English. To the best of our knowledge, there is no gold standard available for evaluating terminology translation quality in MT. For this reason we select an evaluation test set from a legal domain corpus and create a gold standard for evaluating terminology translation in MT. We also propose an error typology taking the terminology translation errors in MT into consideration. We translate sentences of the test set with our MT systems and terminology translations are manually classified as per the error typology. We evaluate the MT system’s performance on terminology translation, and demonstrate our findings, unraveling strengths, weaknesses, and similarities of PB-SMT and NMT in the area of term translation.

Phrase-Based Statistical Machine Translation of Hindi Poetries into English by incorporating Word Sense Disambiguation

Statistical machine translation (SMT) is a variant of machine translation where the translations are handled with statistically defined rules. Numerous researchers have attempted to build the framework which can comprehend the different dialects to translate from one source language to another target language. However, the focus on translation of poetry is less. Reliable and rapid transliteration of the poetry is very mandatory for the execution of the computer to translate the poem from one language to another. The existing approach has several issues, such as, time consumption, quality of the translation process, and matching of similar words. To overcome these issues, we propose a phrase-based statistical machine translation (PSMT) with special adherence to word sense disambiguation (WSD). The quality of the translation is increased by sensing the ambiguous words with WSD. The Hindi WordNet along with the Lesk algorithm identifies the ambiguous words and senses the exact meaning before the phrase extraction. Finally, the proposed method is compared with machine translation schemes, such as, rule-based machine translation and transfer-based machine translation. The experimental results suggest that the proposed method performed well with the inclusion of WSD in the PSMT technique.

Improving neural machine translation through phrase-based soft forced decoding

Compared to traditional statistical machine translation (SMT), such as phrase-based machine translation (PBMT), neural machine translation (NMT) often sacrifices adequacy for the sake of fluency. We propose a method to combine the advantages of traditional SMT and NMT by exploiting an existing phrase-based SMT model to compute the phrase-based decoding cost for an NMT output and then using this cost to rerank the n-best NMT outputs. The main challenge in implementing this approach is that NMT outputs may not be in the search space of the standard phrase-based decoding algorithm, because the search space of PBMT is limited by the phrase-based translation rule table. We propose a phrase-based soft forced decoding algorithm, which can always successfully find a decoding path for any NMT output. We show that using the phrase-based decoding cost to rerank the NMT outputs can successfully improve translation quality on four different language pairs.