Continuous Learning in Neural Machine Translation using Bilingual Dictionaries

Every teacher can probably relate anecdotes about misapplication of dictionary by students.1 Some are real brain busters, like Ich schlafe zuteilen.2 Others Er links das Zimmer, Er haut unter dem Bett, Ich h6re am liebsten Stein und Br6tchen, and Zu Halloween gibt es hier Kniff oder Extragenul3 are more easily decoded. 3 Most students have acquired a bilingual dictionary of some sort by end of second year of college-level German, and even though a teacher may discourage its use, students feel comfortable using their bilingual dictionary whether or not it actually aids understanding. general, students are more favorably disposed towards bilingual dictionaries than are teachers and (Ard 2; see also Kharma). Stark also found learners have a positive attitude towards dictionaries. Not surprisingly then, bilingual dictionary is used by students not as a last resort but rather as a primary tool. Teaching its proper use responds this reality. In many publications on reading and learning, bilingual dictionary use is discouraged or treated only in passing. Baxter maintains students will learn only employ single lexical items if they use bilingual dictionaries. He prefers monolingual dictionaries, as they lead students to use of conversational definition in speech (325).4 The problem, of course, is dictionary definitions are often too difficult understand, as they are not sufficiently contextualized (cf. Kharma). Fischer maintains definitions presuppose knowledge about word usage, and do not specify contexts in which words are used. It seems most dictionaries are written for people who already know language and who can contextualize definitions. Regardless, Laufer found traditional entry which consists of a definition and an example is indeed best possible entry for an average user (141). Under assumption successful readers possess contextual guessing ability, while less successful readers rely heavily on a bilingual dictionary, methodologists advocate developing reading skills like contextual guessing rather than use of bilingual dictionaries (Nation). But, as Summers notes, not all meanings can be inferred, accurately guessed, or negotiated. Some words just have be looked up. Some research suggests a case for teaching proper use of bilingual dictionaries. Benssoussan finds in test situations, there is little difference between students who are allowed use of a bilingual dictionary and those who are not. In addition, the use of a bilingual dictionary while reading can facilitate learning of vocabulary (Luppescu and Day 275), even though there is a trade-off in reading speed. Moreover, Hulstijn (145) has found that words which were deemed [by students] relevant in terms of reaching goal of reading were looked up more frequently than words deemed irrelevant. He has proposed letting students try comprehend a text following their own strategy, either by using a bilingual dictionary or by guessing.

Applying convolutional attention mechanisms and Human Memory Search for effective English-Urdu translation

Machine translation aims to minimize the language barrier between people of different linguistic backgrounds. Machine translation is an automatic translation technique between pairs of different languages. Machine translation using neural network or neural machine translation came into the picture due to several limitation associated with its predecessors which are rule based and statistical based models. For large data sets with a rich range of vocabulary, the neural network machine translation system provides fair translation accuracy. We have observed that there remain very few machine translators dedicated to Indian languages, especially those spoken in the North-East area. So our paper mainly focuses on implementing a neural machine translation system for the English-Assamese language. In this paper we used five different neural machine translation models for English-Assamese language pair using LSTMs and GRUs, along with an attention layer. We have made a comparison analysis based on the performance results of these models. We used BLEU Score to calculate the accuracy of these five models, thus achieving a BLEU score of 34.168%, which was the highest among the five models.

Machine translation is used to implement the translation between different languages. Neural machine translation is one of the most popular machine translation methods which have made a great progress in recent years especially on universal languages. However, domestic translation software for non-universal languages is limited and also needs improving. In this paper, we carry out a practice on neural machine translation from Indonesian to Chinese. We first build a bilingual corpus of Indonesian and Chinese. After that, we train translation models using neural machine translation method, with traditional statistical machine translation models as baselines. In the later stages of our practice, we develop a Web software, named as Lore Translator, basing on our so-far best translation model. The performance of our model is comparable to previous work.

Rare words are usually replaced with a single <;unk> token in the current encoder-decoder style of neural machine translation, challenging the translation modeling by an obscured context. In this article, we propose to build a fuzzy semantic representation (FSR) method for rare words through a hierarchical clustering method to group rare words together, and integrate it into the encoder-decoder framework. This hierarchical structure can compensate for the semantic information in both source and target sides, and providing fuzzy context information to capture the semantic of rare words. The introduced FSR can also alleviate the data sparseness, which is the bottleneck in dealing with rare words in neural machine translation. In particular, our method is easily extended to the transformer-based neural machine translation model and learns the FSRs of all in-vocabulary words to enhance the sentence representations in addition to rare words. Our experiments on Chinese-to-English translation tasks confirm a significant improvement in the translation quality brought by the proposed method.

Success of neural networks in natural language processing has paved the way for neural machine translation (NMT), which rapidly became the mainstream approach in machine translation. Significant improvement in translation performance has been achieved with breakthroughs such as encoder-decoder networks, attention mechanism, and Transformer architecture. However, the necessity of large amounts of parallel data for training an NMT system and rare words in translation corpora are issues yet to be overcome. In this article, we approach NMT of the low-resource Turkish-English language pair. We employ state-of-the-art NMT architectures and data augmentation methods that exploit monolingual corpora. We point out the importance of input representation for the morphologically rich Turkish language and make a comprehensive analysis of linguistically and non-linguistically motivated input segmentation approaches. We prove the effectiveness of morphologically motivated input segmentation for the Turkish language. Moreover, we show the superiority of the Transformer architecture over attentional encoder-decoder models for the Turkish-English language pair. Among the employed data augmentation approaches, we observe back-translation to be the most effective and confirm the benefit of increasing the amount of parallel data on translation quality. This research demonstrates a comprehensive analysis on NMT architectures with different hyperparameters, data augmentation methods, and input representation techniques, and proposes ways of tackling the low-resource setting of Turkish-English NMT.

Intuitively, machine translation (MT) between closely related languages, such as Swedish and Danish, is easier than MT between more distant pairs, such as Finnish and Danish.Yet, the notions of 'closely related' languages and 'easier' translation have so far remained underspecified.Moreover, in the context of neural MT, this assumption was almost exclusively evaluated in scenarios where English was either the source or target language, leaving a broader cross-lingual view unexplored.In this work, we present a controlled study of language similarity and neural MT difficulty for 56 European translation directions.We test a range of language similarity metrics, some of which are reasonable predictors of MT difficulty.On a text-level, we reassess previously introduced indicators of MT difficulty, and find that they are not well-suited to our domain, or neural MT more generally.Ultimately, we hope that this work inspires further cross-lingual investigations of neural MT difficulty.

In this paper, we propose a useful optimization method for low-resource Neural Machine Translation (NMT) by investigating the effectiveness of multiple neural network optimization algorithms.Our results confirm that applying the proposed optimization method on English-Persian translation can exceed translation quality compared to the English-Persian Statistical Machine Translation (SMT) paradigm.

Deep Learning techniques have significant progress in the last few years. Different designs and methods of the model have experimented to enhance the performance in various domains of Natural Language Processing (NLP). Machine Translation is a domain of NLP. In this paper, we have reviewed different Encoding-Decoding methods for Neural Machine Translation(NMT). We also, compare these various methods and put forward a past, present and future of Neural Machine Translation.

Machine Translation (MT) has recently been strengthened by the emergence of deep neural network techniques, which have brought the dream of language translation in community-based practices and clinical practices closer to reality. This chapter introduces the clinical practice of MT, especially in low resource languages. The following are some of the highlights of this chapter. How MT played a crucial role in good social reasons is focused on in this chapter. The chapter starts with the history of translation technologies that have played a vital role in various crisis and relief scenarios as the Haitian earthquake in 2010 and Translators without Borders (TWB), respectively. The Standby Task Force (SBTF) deployed the technology to tackle misinformation during Coronavirus Pandemic 2019. Next, the chapter explores the importance of the MT system, where it describes MT literacy as required across society to impact the healthcare of human beings. It describes the challenges of translation for clinical texts. Some of those are highlighted as (a) Domain: characteristics of clinical text differentiated from texts with other domains, (b) code mixed low-resource languages: noisy clinical data and lower quantity of data in the digital form available for computation, (c) lack of clinical domain corpora, and (d) very rich morphological structure: e.g., procedures (e.g., hepatico-cholangio-jejuno-stomy) and chemicals (e.g., Hydro-xy-nitro-di-hydro-thy-mine). Strategies or approaches to building MT on the clinical text can be categorized as: (1) Rule-based MT (early days), (2) Statistical MT (SMT, one of the successful methods in MT history), and (3) Neural MT (NMT, recent advancements of MT). Both SMT and NMT that work on same grounds by learning from text and are the primary focus of this chapter. L earning transparency for the patient's use of clinical data is an essential component. Much of today's healthcare data is unstructured text, such as clinical text, doctor's notes, nursing notes, lab reports, test reports, and more. A clinical practitioner is faced with a language barrier for communicating with a patient to interpret patient histories, examine a clinical diagnosis, or restate the recommended treatment method and follow-up to aid comprehension. The only way a medical practitioner encourages patients to ask questions or respond to queries is by directing them to input text with the help of MT. Finally, the chapter discusses contemporary techniques with Neural Machine Translation (NMT), namely multilingual, transfer learning on clinical data.

Generative adversarial networks (GANs) has achieved great success in the field of image processing, Adversarial Neural Machine Translation(NMT) is the application of GANs to machine translation. Unlike previous work training NMT model through maximizing the likelihood of the human translation, Adversarial NMT minimizes the distinction between human translation and the translation generated by a NMT model. Even though Adversarial NMT has achieved impressive results, while using little in the way of prior knowledge. In this paper, we integrated bilingual dictionaries to Adversarial NMT by leveraging a character model. Extensive experiment shows that our proposed methods can achieve remarkable improvement on the translation quality of Adversarial NMT, and obtain better result than several strong baselines.

The preservation of domain knowledge from source to the target is crucial in any translation workflows. Hence, translation service providers that use machine translation (MT) in production could reasonably expect that the translation process should transfer both the underlying pragmatics and the semantics of the source-side sentences into the target language. However, recent studies suggest that the MT systems often fail to preserve such crucial information (e.g., sentiment, emotion, gender traits) embedded in the source text in the target. In this context, the raw automatic translations are often directly fed to other natural language processing (NLP) applications (e.g., sentiment classifier) in a cross-lingual platform. Hence, the loss of such crucial information during the translation could negatively affect the performance of such downstream NLP tasks that heavily rely on the output of the MT systems. In our current research, we carefully balance both the sides (i.e., sentiment and semantics) during translation, by controlling a global-attention-based neural MT (NMT), to generate translations that encode the underlying sentiment of a source sentence while preserving its non-opinionated semantic content. Toward this, we use a state-of-the-art reinforcement learning method, namely, actor-critic , that includes a novel reward combination module, to fine-tune the NMT system so that it learns to generate translations that are best suited for a downstream task, viz. sentiment classification while ensuring the source-side semantics is intact in the process. Experimental results for Hindi–English language pair show that our proposed method significantly improves the performance of the sentiment classifier and alongside results in an improved NMT system.

Problem statement: Any Arabic to English Machine Translation (MT) system should be capable of dealing with word order which Arabic exhibits. This poses a significant challenge to MT due to the vast number of ways to express the same sentence in Arabic. The ordering features are very important and should be carefully applied to ensure the generation of sentence in the target language. Because they apply to the target language, it shoul d fulfill the specific requirement of this language . Mistakes in the MT output can be either the result of analysis problems at the source language level, or due to generation problem at target language level. Word order rules are crucial for the generation of sentences in the target language. They also serve a s rules for the ordering of sentence constituents. These rules draw their information from the syntact ic knowledge. The word order problem becomes more obvious when making machine translation between languages that have rich morphological variations. Approach: The main objective of this research is to develop a machine translation that translates Arabic noun phrases into English by usin g transfer-based approach. A system called Npae- Rbmt has been developed in this research. Transfer- based machine translation is one instance of rule- based machine-translation approaches and is current ly one of the most widely used methods of machine translation. The idea of transfer-based mac hine translation it is necessary to have an intermediate representation that captures the mean ing of the original sentence in order to generate the correct translation. Using advantages of transf er-based machine translation such as analysis step, the Transfer-based becomes simpler as linguistic an alysis goes deeper-as the representation of analysi s step becomes more abstract. In fact, a major goal o f MT research is to define a level of analysis whic h is so deep in which transfer-based machine translat ion is able to do. Results: The method was tested on 88 thesis titles and journals from the computer science domain. The accuracy of the result was 94.6%. These results proved the viability of this a pproach for distant languages. Conclusion: Based on the achieved results, we have managed to perform th e syntactic reordering within an Arabic noun phrases to English translation task by using transf er-based machine translation and also achieved reasonable improvements in translation quality over related approach.

We conduct the first experiment in the literature in which a novel is translated automatically and then post-edited by professional literary translators. Our case study is Warbreaker, a popular fantasy novel originally written in English, which we translate into Catalan. We translated one chapter of the novel (over 3,700 words, 330 sentences) with two data-driven approaches to Machine Translation (MT): phrase-based statistical MT (PBMT) and neural MT (NMT). Both systems are tailored to novels; they are trained on over 100 million words of fiction. In the post-editing experiment, six professional translators with previous experience in literary translation translate subsets of this chapter under three alternating conditions: from scratch (the norm in the novel translation industry), post-editing PBMT, and post-editing NMT. We record all the keystrokes, the time taken to translate each sentence, as well as the number of pauses and their duration. Based on these measurements, and using mixed-effects models, we study post-editing effort across its three commonly studied dimensions: temporal, technical and cognitive. We observe that both MT approaches result in increases in translation productivity: PBMT by 18%, and NMT by 36%. Post-editing also leads to reductions in the number of keystrokes: by 9% with PBMT, and by 23% with NMT. Finally, regarding cognitive effort, post-editing results in fewer (29 and 42% less with PBMT and NMT, respectively) but longer pauses (14 and 25%).

Whether test takers should be allowed access to dictionaries when taking L2 tests has been the subject of debate for a good number of years. Opinions differ according to how the test construct is understood and whether the underlying value system favours process-orientated assessment for learning, with its concern to elicit the test takers' best performance, or product-focused assessment of learning, with its emphasis on the discriminatory power of the test. One key study into bilingual dictionaries and writing tests (Hurman &amp; Tall, 1998) concluded that dictionary use improves test scores. This study was influential in a recent decision to ban dictionaries in several high-stakes L2 examinations in the UK. Research into dictionary use in reading tests has suggested, however, that dictionary availability makes no statistically significant difference to test scores. This article presents the findings of a further study into bilingual dictionary use in writing tests that also indicated no significant difference to scores. Considering this finding alongside those of studies other than Hurman and Tall's casts some doubt on whether the UK ban was fully justified.