English-French Translation Research Articles

Adaptive multi-task learning for speech to text translation

End-to-end speech to text translation aims to directly translate speech from one language into text in another, posing a challenging cross-modal task particularly in scenarios of limited data. Multi-task learning serves as an effective strategy for knowledge sharing between speech translation and machine translation, which allows models to leverage extensive machine translation data to learn the mapping between source and target languages, thereby improving the performance of speech translation. However, in multi-task learning, finding a set of weights that balances various tasks is challenging and computationally expensive. We proposed an adaptive multi-task learning method to dynamically adjust multi-task weights based on the proportional losses incurred during training, enabling adaptive balance in multi-task learning for speech to text translation. Moreover, inherent representation disparities across different modalities impede speech translation models from harnessing textual data effectively. To bridge the gap across different modalities, we proposed to apply optimal transport in the input of end-to-end model to find the alignment between speech and text sequences and learn the shared representations between them. Experimental results show that our method effectively improved the performance on the Tibetan-Chinese, English-German, and English-French speech translation datasets.

Occurrence of Ellipsis and Shift in French-English Translation: A Study of <i>Madame Bovary</i>

Ellipsis is a cohesive device that omits an element or elements in a sentence whose interpretation depends on presupposition in the context; it is about linguistic changes that occur in translation. This study aims to describe ellipsis, shift and their effect on meaning in French-English translation. The study is a qualitative research study carried out manually on <i>Madame Bovary</i>. The novel is wholly read, and passages of the novel which demonstrate cohesive devices of ellipsis and shift are selected and analysed. This study is supported by Halliday and Hasan’s theory (1976) of textual cohesion and Catford’s theory (1965) of translation shifts. The analysis reveals that English is more elliptical, whereas French is more demonstrative due to some language peculiarities and language norms. It specifies that some language peculiarities (concreteness and abstractness) and language norms (language usage options) are determinants of the translation procedures of ellipsis from French into English. Class shift and modulation are the translation procedures that are more functional than other shift categories and translation procedures in dealing with ellipses in French-English translation.

Contrasting Relativization in some Naomi Alderman’s Novels and their French Translation from a Syntactic and a Semantic Perspectives

Language in usage is the result of various operations. Linguistic operations are worth studying so as to uncover the subtleties which make languages to be unique in their inner organization. These operations occur within various linguistic units (words, phrases, clauses, sentences, paragraphs, and texts) and can be studied at various levels of linguistic analysis (Dutoit, 2000). Provided the wide range of such operations, the notion of clause operations is therefore the subject of this article; more specifically, this study intends to contrast relativization from a syntactic and semantic point of view based on an English-French translation corpus (extracted from three novels by Naomi Alderman and their French translations). With the aid of the Meaning-Text Theory (MTT), the findings suggest that there are convergent and divergent syntactic properties, shared syntactic processes, and common syntactic functions related to the translational renderings of relative markers. Moreover, the contrastive analysis of relativization from a semantic viewpoint reveals some semantic functions undertaken by relative markers, some correspondence types between relatives of different versions of the corpus, and some translation procedures used by translators while rendering the overall meaning of the source text.

The Function and Manipulation of Demonstrative Reference in French-English Translation

The Function and Manipulation of Demonstrative Reference in French-English Translation

Design of Transformer Based English French Translation Model

Design of Transformer Based English French Translation Model

Curriculum Compositional Continual Learning for Neural Machine Translation

Current trends in language modelling leverage large language models pre-trained on a huge corpus of data to achieve state of the art results on several NLP tasks. On the other hand, humans acquire language from small amount of data using cognitive principles. Recently, a continual learning approach using compositionality to disentangle the syntax and semantics of an input sentence for downstream sequence to sequence tasks was proposed. In this work, we show how curriculum learning can be incorporated with this framework to improve performance. More specifically, first, we show that using the model of interest with reduced hidden size as the auxiliary model to generate curriculum is not necessarily optimal and second, we propose a novel variant of the one best score approach for curriculum learning where, a sequence to sequence model is used as the auxiliary model to generate the conditional probabilities of word predictions (proxy for difficulty) and consequently used this to generate a curriculum. Results on a variety of translation tasks, demonstrate the superiority of the proposed approach compared to several baselines, enabling the improvement of sentence accuracy with respect to knowledge transfer and catastrophic-forgetting both by at least a significant margin of 35% with respect to the best performing baseline on the English-French translation task.

Recurrent Errors in the French-English Translations of Undergrad Students in the University of Bangui

While translation is indispensable in multi-lingual contexts, translation from French to English continues to pose a serious problem to students of translation in the University of Bangui. This study was designed to identify first year students’ errors in their translation from French to English in order to suggest areas where adjustments can be made to improve on their proficiencies and translation skills. From the analysis of 186 learners’ French-English translations, we identified 2250 inter language errors which were mostly in the use of the continuous aspects, tense concords and subject omission. Consequently, we proposed that while focus could be made to help the learners avoid the deviations, it is imperative to get them to understand more acceptable alternatives to enhance their proficiencies and French-English translation skills.

On the Role of English-French Translation in French Teaching Under Language Transfer Theory

On the Role of English-French Translation in French Teaching Under Language Transfer Theory

X-Transformer: A Machine Translation Model Enhanced by the Self-Attention Mechanism

Machine translation has received significant attention in the field of natural language processing not only because of its challenges but also due to the translation needs that arise in the daily life of modern people. In this study, we design a new machine translation model named X-Transformer, which refines the original Transformer model regarding three aspects. First, the model parameter of the encoder is compressed. Second, the encoder structure is modified by adopting two layers of the self-attention mechanism consecutively and reducing the point-wise feed forward layer to help the model understand the semantic structure of sentences precisely. Third, we streamline the decoder model size, while maintaining the accuracy. Through experiments, we demonstrate that having a large number of decoder layers not only affects the performance of the translation model but also increases the inference time. The X-Transformer reaches the state-of-the-art result of 46.63 and 55.63 points in the BiLingual Evaluation Understudy (BLEU) metric of the World Machine Translation (WMT), from 2014, using the English–German and English–French translation corpora, thus outperforming the Transformer model with 19 and 18 BLEU points, respectively. The X-Transformer significantly reduces the training time to only 1/3 times that of the Transformer. In addition, the heat maps of the X-Transformer reach token-level precision (i.e., token-to-token attention), while the Transformer model remains at the sentence level (i.e., token-to-sentence attention).

Word-Region Alignment-Guided Multimodal Neural Machine Translation

We propose word-region alignment-guided multimodal neural machine translation (MNMT), a novel model for MNMT that links the semantic correlation between textual and visual modalities using word-region alignment (WRA). Existing studies on MNMT have mainly focused on the effect of integrating visual and textual modalities. However, they do not leverage the semantic relevance between the two modalities. We advance the semantic correlation between textual and visual modalities in MNMT by incorporating WRA as a bridge. This proposal has been implemented on two mainstream architectures of neural machine translation (NMT): the recurrent neural network (RNN) and the transformer. Experiments on two public benchmarks, English–German and English–French translation tasks using the Multi30k dataset and English–Japanese translation tasks using the Flickr30kEnt-JP dataset prove that our model has a significant improvement with respect to the competitive baselines across different evaluation metrics and outperforms most of the existing MNMT models. For example, 1.0 BLEU scores are improved for the English–German task and 1.1 BLEU scores are improved for the English–French task on the Multi30k test2016 set; and 0.7 BLEU scores are improved for the English–Japanese task on the Flickr30kEnt-JP test set. Further analysis demonstrates that our model can achieve better translation performance by integrating WRA, leading to better visual information use.

“French-English Translation in Canada” by Maynard Gertler


 
 
 
 “French-English Translation in Canada” is the transcript of a talk given by Montreal publisher Maynard Gertler to an unidentified audience in 1976. When Gertler founded Harvest House in 1959, his aim was to issue the first English-language translations of the works of Québécois writers in inexpensive, accessible editions. The talk is a document of enduring value that provides incisive analysis of contemporary Canadian publishing and presents the challenges facing a domestic publisher who was committed to issuing French works in English translation.
 
 
 
 
 
 

Machine Translation Utilizing the Frequent-Item Set Concept.

In this paper, we introduce new concepts in the machine translation paradigm. We treat the corpus as a database of frequent word sets. A translation request triggers association rules joining phrases present in the source language, and phrases present in the target language. It has to be noted that a sequential scan of the corpus for such phrases will increase the response time in an unexpected manner. We introduce the pre-processing of the bilingual corpus through proposing a data structure called Corpus-Trie (CT) that renders a bilingual parallel corpus in a compact data structure representing frequent data items sets. We also present algorithms which utilize the CT to respond to translation requests and explore novel techniques in exhaustive experiments. Experiments were performed on specific language pairs, although the proposed method is not restricted to any specific language. Moreover, the proposed Corpus-Trie can be extended from bilingual corpora to accommodate multi-language corpora. Experiments indicated that the response time of a translation request is logarithmic to the count of unrepeated phrases in the original bilingual corpus (and thus, the Corpus-Trie size). In practical situations, 5–20% of the log of the number of the nodes have to be visited. The experimental results indicate that the BLEU score for the proposed CT system increases with the size of the number of phrases in the CT, for both English-Arabic and English-French translations. The proposed CT system was demonstrated to be better than both Omega-T and Apertium in quality of translation from a corpus size exceeding 1,600,000 phrases for English-Arabic translation, and 300,000 phrases for English-French translation.

INSIGHTS INTO TECHNICAL TRANSLATION COURSE DESIGN

This article offers theoretical and pragmatic insights into the nature of technical translation course design. In so doing, I first provide a definition of specialized translation based on a survey of the literature in this field, conducted collaboratively with a research assistant. Then, I present a comparative table sourcing how technical translation has been taught, as a university course, across Canadian higher education institutions. Following this, I offer a rationale for student-oriented ways of teaching this course, all the while giving concrete steps to co-explore novel topics with undergraduate and graduate students. Finally, I generate a series of considerations and questions for further inquiry into the instruction of technical translation in Canada and worldwide. Keywords: technical translation, specialized translation, English-French translation, translation pedagogy, course design

Re-Transformer: A Self-Attention Based Model for Machine Translation

Machine translation is one of the most popular and hardest tasks in Natural Language Processing. This paper proposes a self-attention based model for machine translation, named Re-Transformer, by transforming the Transformer [1]. Different from prevailing approach through module or GPU stacking to improve the system performance, Re-Transformer modifies the basic architecture; there are four refinements as follows. First, Re-Transformer adopts sub-word Tokenization in corpus preprocessing to overcome rare words. In the encoder layer, dual Self-Attention stacks and less Point Wise Feed Forward layer are adopted to obtain better comprehension of an input sentence. In decoder, reduced the stack of “Decoder” are used to speedup training and inferring speed meanwhile keeps the same level of BLEU. The experiment results show that Re-Transformer with BLEU metric score 31.36, 38.45 (four-layer decoder) and 32.14, 55.62 (two-layer decoder) improves around 4 and 17 points of BLEU metric against the Transformer over the WMT 2014 English-German and English-French Translation Corpus.

A Linguistic Analysis of Cultural Content in French-English Translation of a Yoghurt Commercial

Advertising translation is a multifaceted practice which poses specific challenges for translators that extend beyond sheer linguistic competence of the professionals involved in the process. Cross-cultural awareness and sensitivity are called for when dealing with translating commercial matter internationally and interculturally. This paper presents a comparative analysis of a TV commercial of natural yoghurt and its representation in two languages. The advert was originally created in French, subsequently translated and dubbed in English by a French-accent English speaker. The English version deviates slightly linguistically and culturally from its French counterpart. The notions of explicitation, equivalence, adaptation and localisation applied in this paper provide grounds for analysis of a range of translation decisions and strategies which allow to achieve similar advertising pragmatic effects as well as add extra dimensions that are absent in the source text.

Speed Up the Training of Neural Machine Translation

Neural machine translation (NMT) has achieved notable achievements in recent years. Although existing models provide reasonable translation performance, they cost too much training time. Especially, when the corpus is enormous, their computational cost will be extremely high. In this paper, we propose a novel NMT model based on the conventional bidirectional recurrent neural network (bi-RNN). In this model, we apply a tanh activation function, which can learn the future and history context information more sufficiently, to speed up the training process. Experimental results on tasks of German–English and English–French translation demonstrate that the proposed model can save much training time compared with the state-of-the-art models and provide better translation performances.

Neural Machine Translation with Deep Attention.

Deepening neural models has been proven very successful in improving the model's capacity when solving complex learning tasks, such as the machine translation task. Previous efforts on deep neural machine translation mainly focus on the encoder and the decoder, while little on the attention mechanism. However, the attention mechanism is of vital importance to induce the translation correspondence between different languages where shallow neural networks are relatively insufficient, especially when the encoder and decoder are deep. In this paper, we propose a deep attention model (DeepAtt). Based on the low-level attention information, DeepAtt is capable of automatically determining what should be passed or suppressed from the corresponding encoder layer so as to make the distributed representation appropriate for high-level attention and translation. We conduct experiments on NIST Chinese-English, WMT English-German, and WMT English-French translation tasks, where, with five attention layers, DeepAtt yields very competitive performance against the state-of-the-art results. We empirically find that with an adequate increase of attention layers, DeepAtt tends to produce more accurate attention weights. An in-depth analysis on the translation of important context words further reveals that DeepAtt significantly improves the faithfulness of system translations.

Trading and Translating: English Literature in Rouen, 1730–56

In this period the city of Rouen is known for commercial activity and for certain literary connections, but its status as a centre of sorts for English-French translation has gone unrecognized. This paper explores the writers involved (some well known, some less familiar), the rationales for their translations (particularly from the poetry of Alexander Pope), and their relation on the one hand to the commercial life of Rouen, on the other to its Académie Royale, founded in 1744.

Optimizing Non-Decomposable Evaluation Metrics for Neural Machine Translation

While optimizing model parameters with respect to evaluation metrics has recently proven to benefit end to-end neural machine translation (NMT), the evaluation metrics used in the training are restricted to be defined at the sentence level to facilitate online learning algorithms. This is undesirable because the final evaluation metrics used in the testing phase are usually non-decomposable (i.e., they are defined at the corpus level and cannot be expressed as the sum of sentence-level metrics). To minimize the discrepancy between the training and the testing, we propose to extend the minimum risk training (MRT) algorithm to take non-decomposable corpus-level evaluation metrics into consideration while still keeping the advantages of online training. This can be done by calculating corpus-level evaluation metrics on a subset of training data at each step in online training. Experiments on Chinese-English and English-French translation show that our approach improves the correlation between training and testing and significantly outperforms the MRT algorithm using decomposable evaluation metrics.

English-French Translation of Igbo Traditional Marriage Items: A Semiotic Approach

Culture is the people’s way of life including their beliefs and customs. Traditional marriage in Igbo land is symbolic because it reflects the Igbo man’s ideology and idiosyncrasies This could be seen in the different gift items brought by the bridegroom to the family of the bride before the bride‘s kindred officially and socially legalize the marriage The items differ slightly from one locality to another and from one Igbo community to another. These cultural items that must be presented on the day of one’s traditional marriage( otherwise called ‘igba nkwu nwanyi ’okuko onye uwa or igbu ewu nna ) by the groom are quiet elaborate and very significant. It is a must in Igbo land that any man who seeks the hand of an Igbo lady in marriage must concur to the provision of such items as they are listed. Alternatively, he could give the money equivalent of the items. The thrust of this paper is to translate the frequently listed items from English to French, analyze them and ex-ray their significance and meaning as they are given and received. The paper also investigates the various stages of traditional marriage in Igbo land precisely in Anambra State. DOI: 10.5901/mjss.2016.v7n1s1p311