Kliknij ten link, aby zobaczyć inne rodzaje publikacji na ten temat: Domain translation.
Artykuły w czasopismach na temat „Domain translation”
Utwórz poprawne odniesienie w stylach APA, MLA, Chicago, Harvard i wielu innych
Sprawdź 50 najlepszych artykułów w czasopismach naukowych na temat „Domain translation”.
Przycisk „Dodaj do bibliografii” jest dostępny obok każdej pracy w bibliografii. Użyj go – a my automatycznie utworzymy odniesienie bibliograficzne do wybranej pracy w stylu cytowania, którego potrzebujesz: APA, MLA, Harvard, Chicago, Vancouver itp.
Możesz również pobrać pełny tekst publikacji naukowej w formacie „.pdf” i przeczytać adnotację do pracy online, jeśli odpowiednie parametry są dostępne w metadanych.
Przeglądaj artykuły w czasopismach z różnych dziedzin i twórz odpowiednie bibliografie.
1
Li, Rumeng, Xun Wang i Hong Yu. "MetaMT, a Meta Learning Method Leveraging Multiple Domain Data for Low Resource Machine Translation". Proceedings of the AAAI Conference on Artificial Intelligence 34, nr 05 (3.04.2020): 8245–52. http://dx.doi.org/10.1609/aaai.v34i05.6339.
Pełny tekst źródłaStreszczenie:
Neural machine translation (NMT) models have achieved state-of-the-art translation quality with a large quantity of parallel corpora available. However, their performance suffers significantly when it comes to domain-specific translations, in which training data are usually scarce. In this paper, we present a novel NMT model with a new word embedding transition technique for fast domain adaption. We propose to split parameters in the model into two groups: model parameters and meta parameters. The former are used to model the translation while the latter are used to adjust the representational space to generalize the model to different domains. We mimic the domain adaptation of the machine translation model to low-resource domains using multiple translation tasks on different domains. A new training strategy based on meta-learning is developed along with the proposed model to update the model parameters and meta parameters alternately. Experiments on datasets of different domains showed substantial improvements of NMT performances on a limited amount of data.
2
Djebaili, Baya. "ترجمة النص المالي". Traduction et Langues 14, nr 1 (31.08.2015): 243–54. http://dx.doi.org/10.52919/translang.v14i1.787.
Pełny tekst źródłaStreszczenie:
Financial Text Translation
Nowadays, specialized translation has acquired a great importance in different fields, particularly in the domain of affairs and finance. The domains covered by financial translation are various. They range from simple economic research to the most complex accounting studies. It is thus necessary for this translation to have a deep knowledge of the issue to be tackled, and a total mastery of the mechanisms of finance. Translating the financial terminology is the greatest obstacle that a translator meets in his work. This is due to its technical nature as well as the different neologisms regularly used in the language of finance. The most important element of this piece of work is the importance of research in both documentation and terminology. If these two elements are properly carried out, they allow the translator to translate any specialized text in any field without necessarily being a specialist in the domain in question. Nevertheless, he must usually carry out continuous research and have a universal knowledge. He also has to enrich and update his databases and terminological files to make of his translation a driving force for the coming translations.
3
Marie, Benjamin, i Atsushi Fujita. "Synthesizing Parallel Data of User-Generated Texts with Zero-Shot Neural Machine Translation". Transactions of the Association for Computational Linguistics 8 (listopad 2020): 710–25. http://dx.doi.org/10.1162/tacl_a_00341.
Pełny tekst źródłaStreszczenie:
Neural machine translation (NMT) systems are usually trained on clean parallel data. They can perform very well for translating clean in-domain texts. However, as demonstrated by previous work, the translation quality significantly worsens when translating noisy texts, such as user-generated texts (UGT) from online social media. Given the lack of parallel data of UGT that can be used to train or adapt NMT systems, we synthesize parallel data of UGT, exploiting monolingual data of UGT through crosslingual language model pre-training and zero-shot NMT systems. This paper presents two different but complementary approaches: One alters given clean parallel data into UGT-like parallel data whereas the other generates translations from monolingual data of UGT. On the MTNT translation tasks, we show that our synthesized parallel data can lead to better NMT systems for UGT while making them more robust in translating texts from various domains and styles.
4
Xiang, Cailing. "Study on the Effectiveness of ChatGPT in Translating Forestry Sci-tech Texts". International Journal of Linguistics, Literature and Translation 7, nr 9 (29.08.2024): 88–94. http://dx.doi.org/10.32996/ijllt.2024.7.9.11.
Pełny tekst źródłaStreszczenie:
ChatGPT, an advanced language model by OpenAI, enhances translation with its powerful language generation and understanding. In comparison to traditional human translation, ChatGPT is less costly, time-consuming, and knowledge-constraint, showcasing the substantial value of its application in translation practice. In the context of globalization, forestry translation plays an increasing role in facilitating global forestry development. To meet the growing need for efficient and high-quality translation in the forestry sector, this paper did research on the effectiveness of ChatGPT in the translation of forestry sci-tech texts. Combining quantitative analysis using BLEU and TER scores with qualitative evaluations by domain experts, this study compares the quality of translations produced by ChatGPT with that of the three mainstream machine translation tools in the market—Google Translate, Youdao Translation, and DeepL Translator regarding the translations’ accuracy and readability. The findings reveal that while ChatGPT excels in domain-specific terminology and context-sensitive meanings, it faces challenges in dealing with texts with special sentence structures and making the translations adaptable. By identifying the strengths and limitations of ChatGPT in translating forestry sci-tech texts, this research illustrates that there is great potential for ChatGPT’s application in forestry translation. Additionally, the study provides insights that can guide the development and refinement of machine translation systems to better meet the needs of specialized fields, ultimately facilitating more effective global communication and knowledge sharing.
5
Sokolova, Natalia. "Machine vs Human Translation in the Synergetic Translation Space". Vestnik Volgogradskogo gosudarstvennogo universiteta. Serija 2. Jazykoznanije, nr 6 (luty 2021): 89–98. http://dx.doi.org/10.15688/jvolsu2.2021.6.8.
Pełny tekst źródłaStreszczenie:
The paper focuses on English-to-Russian translations of patent applications on the website of the World Intellectual Property Organization (WIPO). A comparative analysis of patent applications is performed by using translations made with the help of the WIPO Translate tool and human translators within the framework of the synergetic translation space concept encompassing the domains of the author's intensions, text content and composition, energy, translator, recipient, and the translation acceptability notion. The translation erratology aspects were considered from the point of view of the semantic, referential, and syntactic ambiguity within the domains of content-composition and energy space. In the domain of the author, the intention to convey some technical information is revealed, while its rendering in the content-composition and energy domains depends on whether the translation is made by a person or a machine. Genre- and composition-related specifics have been rendered in both cases while machine translation errors have been proven to result from the semantic, referential, or syntactic ambiguity, and this is when the translated output is generally considered unacceptable by the recipient. The results obtained can be used for editing machine translations of patent documentation, assessing the quality of technical documentation translation that is referred to other specific genre conventions.
6
Yin, Xu, Yan Li i Byeong-Seok Shin. "DAGAN: A Domain-Aware Method for Image-to-Image Translations". Complexity 2020 (28.03.2020): 1–15. http://dx.doi.org/10.1155/2020/9341907.
Pełny tekst źródłaStreszczenie:
The image-to-image translation method aims to learn inter-domain mappings from paired/unpaired data. Although this technique has been widely used for visual predication tasks—such as classification and image segmentation—and achieved great results, we still failed to perform flexible translations when attempting to learn different mappings, especially for images containing multiple instances. To tackle this problem, we propose a generative framework DAGAN (Domain-aware Generative Adversarial etwork) that enables domains to learn diverse mapping relationships. We assumed that an image is composed with background and instance domain and then fed them into different translation networks. Lastly, we integrated the translated domains into a complete image with smoothed labels to maintain realism. We examined the instance-aware framework on datasets generated by YOLO and confirmed that this is capable of generating images of equal or better diversity compared to current translation models.
7
Bernaerts, Lars, Liesbeth De Bleeker i July De Wilde. "Narration and translation". Language and Literature: International Journal of Stylistics 23, nr 3 (31.07.2014): 203–12. http://dx.doi.org/10.1177/0963947014536504.
Pełny tekst źródłaStreszczenie:
This opening essay of the special issue on ‘Narration and Translation’ discusses the overlaps between the fields of narratology and translation studies. The fact that translation scholars have merely skimmed the surface of narratological issues relevant for the study of translation can be understood within the context of early developments in translation studies. The first explicit use of narratological models in this discipline has grown out of unease with the extant focus on the macrostructural level of translations. In recent decades, translation scholars have begun to include narrative approaches in their research. Some conceptualize the translator’s discursive presence by referring to a model of narrative communication, or borrow concepts from narratology in order to analyse observed shifts in literary translations. Outside the domain of literary translation studies, scholars have looked into the way translation can refashion narratives in the real world. Conversely, narrative theories have rarely dealt with translational issues, even though they often rely on translations of literary texts. The issue as a whole wants to enhance the dialogue between narratology and translation studies. Each essay explores aspects of the relation between narration and translation.
8
Dai, Diwei. "A Study on Application of Construal Theory in English Translation of Chinese Medical book: take English Translation of Jin Gui Yao Liao as an Example". International Journal of Public Health and Medical Research 1, nr 1 (25.03.2024): 20–28. http://dx.doi.org/10.62051/ijphmr.v1n1.03.
Pełny tekst źródłaStreszczenie:
The translation of Chinese medical books is characterized by language, cultural connotation and cognitive domain background, which makes the translators encounter different levels of difficulty in the process of translation and form different translations accordingly. This paper takes the construal theory in cognitive linguistics as a guide, analyzes the important role of four kinds of means of construal in the process of translating Chinese medical books, and analyzes the different English translations of JGL under the construal theory, analyzes that different translations reflect different cognitive mechanisms of the translators, and comes to the conclusion that the translations should maximally reflect the cognitive points of reference of the authors at that time, so as to maximize the translations. It is also concluded that the translation should maximally reflect the author's cognitive reference point so as to maximize the closeness of the translation to the original text, aiming to provide theoretical guidance and reference for the English translation of Chinese medical books.
9
Karatsiolis, Savvas, Christos N. Schizas i Nicolai Petkov. "Modular domain-to-domain translation network". Neural Computing and Applications 32, nr 11 (26.07.2019): 6779–91. http://dx.doi.org/10.1007/s00521-019-04358-8.
Pełny tekst źródła
10
Marie, Benjamin, i Atsushi Fujita. "Phrase Table Induction Using In-Domain Monolingual Data for Domain Adaptation in Statistical Machine Translation". Transactions of the Association for Computational Linguistics 5 (grudzień 2017): 487–500. http://dx.doi.org/10.1162/tacl_a_00075.
Pełny tekst źródłaStreszczenie:
We present a new framework to induce an in-domain phrase table from in-domain monolingual data that can be used to adapt a general-domain statistical machine translation system to the targeted domain. Our method first compiles sets of phrases in source and target languages separately and generates candidate phrase pairs by taking the Cartesian product of the two phrase sets. It then computes inexpensive features for each candidate phrase pair and filters them using a supervised classifier in order to induce an in-domain phrase table. We experimented on the language pair English–French, both translation directions, in two domains and obtained consistently better results than a strong baseline system that uses an in-domain bilingual lexicon. We also conducted an error analysis that showed the induced phrase tables proposed useful translations, especially for words and phrases unseen in the parallel data used to train the general-domain baseline system.
11
Pham, MinhQuang, Josep Maria Crego i François Yvon. "Revisiting Multi-Domain Machine Translation". Transactions of the Association for Computational Linguistics 9 (luty 2021): 17–35. http://dx.doi.org/10.1162/tacl_a_00351.
Pełny tekst źródłaStreszczenie:
When building machine translation systems, one often needs to make the best out of heterogeneous sets of parallel data in training, and to robustly handle inputs from unexpected domains in testing. This multi-domain scenario has attracted a lot of recent work that fall under the general umbrella of transfer learning. In this study, we revisit multi-domain machine translation, with the aim to formulate the motivations for developing such systems and the associated expectations with respect to performance. Our experiments with a large sample of multi-domain systems show that most of these expectations are hardly met and suggest that further work is needed to better analyze the current behaviour of multi-domain systems and to make them fully hold their promises.
12
Hanić, Jasmina, Tanja Pavlović i Alma Jahić. "Translating emotion-related metaphors: A cognitive approach". ExELL 4, nr 2 (1.12.2016): 87–101. http://dx.doi.org/10.1515/exell-2017-0008.
Pełny tekst źródłaStreszczenie:
Abstract The paper explores the existence of cognitive linguistics principles in translation of emotion-related metaphorical expressions. Cognitive linguists (Lakoff & Johnson, 1980; Lakoff, 1987) define metaphor as a mechanism used for understanding one conceptual domain, target domain, in terms of another conceptual domain, source domain, through sets of correspondences between these two domains. They also claim that metaphor is omnipresent in ordinary discourse. Cognitive linguists, however, also realized that certain metaphors can be recognized and identified in different languages and cultures whereas some are language- and culture-specific. This paper focuses on similarities and variations in metaphors which have recently become popular within the discipline of Translation Studies. Transferring and translating metaphors from one language to another can represent a challenge for translators due to a multi-faceted process of translation including both linguistic and non-linguistic elements. A number of methods and procedures have been developed to overcome potential difficulties in translating metaphorical expressions, with the most frequent ones being substitution, paraphrase, or deletion. The analysis shows the transformation of metaphorical expressions from one language into another and the procedures involving underlying conceptual metaphors, native speaker competence, and the influence of the source language.
13
Liang, Jianze, Chengqi Zhao, Mingxuan Wang, Xipeng Qiu i Lei Li. "Finding Sparse Structures for Domain Specific Neural Machine Translation". Proceedings of the AAAI Conference on Artificial Intelligence 35, nr 15 (18.05.2021): 13333–42. http://dx.doi.org/10.1609/aaai.v35i15.17574.
Pełny tekst źródłaStreszczenie:
Neural machine translation often adopts the fine-tuning approach to adapt to specific domains. However, nonrestricted fine-tuning can easily degrade on the general domain and over-fit to the target domain. To mitigate the issue, we propose Prune-Tune, a novel domain adaptation method via gradual pruning. It learns tiny domain-specific sub-networks during fine-tuning on new domains. Prune-Tune alleviates the over-fitting and the degradation problem without model modification. Furthermore, Prune-Tune is able to sequentially learn a single network with multiple disjoint domain-specific sub-networks for multiple domains. Empirical experiment results show that Prune-Tune outperforms several strong competitors in the target domain test set without sacrificing the quality on the general domain in both single and multi-domain settings. The source code and data are available at https://github.com/ohlionel/Prune-Tune.
14
Nielsen, Sandro. "Bilingual Dictionaries for Communication in the Domain of Economics: Function-Based Translation Dictionaries". HERMES - Journal of Language and Communication in Business 27, nr 54 (22.12.2015): 161. http://dx.doi.org/10.7146/hjlcb.v27i54.22953.
Pełny tekst źródłaStreszczenie:
<p>With their focus on terms, bilingual dictionaries are important tools for translating texts on economics. The most common type is the multi-field dictionary covering several related subject fields; however, multi-field dictionaries treat one or few fields extensively thereby neglecting other fields in contrast to single-field and sub-field dictionaries. Furthermore, recent research shows that economic translation is not limited to terms so lexicographers who identify and analyse the needs of translators, usage situations and stages in translating economic texts will have a sound basis for designing their lexicographic tools. The function theory allows lexicographers to study these basics so that they can offer translation tools to the domain of economics. Dictionaries should include data about terms, their grammatical properties, and their combinatorial potential as well as language varieties such as British, American and international English to indicate syntactic options and restrictions on language use. Secondly, translators need to know the meaning of domain-specific terms to properly understand the differences in the structure of the domains in the cultures involved. Finally, pragmatic data will tell authors and translators how textual resources are conventionally used and what is textually appropriate in communication within the fi eld of economics. The focus will mainly be on translations between Danish and English.</p>
15
Saunders, Danielle. "Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey". Journal of Artificial Intelligence Research 75 (29.09.2022): 351–424. http://dx.doi.org/10.1613/jair.1.13566.
Pełny tekst źródłaStreszczenie:
The development of deep learning techniques has allowed Neural Machine Translation (NMT) models to become extremely powerful, given sufficient training data and training time. However, systems struggle when translating text from a new domain with a distinct style or vocabulary. Fine-tuning on in-domain data allows good domain adaptation, but requires sufficient relevant bilingual data. Even if this is available, simple fine-tuning can cause overfitting to new data and catastrophic forgetting of previously learned behaviour. We survey approaches to domain adaptation for NMT, particularly where a system may need to translate across multiple domains. We divide techniques into those revolving around data selection or generation, model architecture, parameter adaptation procedure, and inference procedure. We finally highlight the benefits of domain adaptation and multidomain adaptation techniques to other lines of NMT research.
16
Macketanz, Vivien, Eleftherios Avramidis, Aljoscha Burchardt, Jindrich Helcl i Ankit Srivastava. "Machine Translation: Phrase-Based, Rule-Based and Neural Approaches with Linguistic Evaluation". Cybernetics and Information Technologies 17, nr 2 (1.06.2017): 28–43. http://dx.doi.org/10.1515/cait-2017-0014.
Pełny tekst źródłaStreszczenie:
Abstract In this article we present a novel linguistically driven evaluation method and apply it to the main approaches of Machine Translation (Rule-based, Phrase-based, Neural) to gain insights into their strengths and weaknesses in much more detail than provided by current evaluation schemes. Translating between two languages requires substantial modelling of knowledge about the two languages, about translation, and about the world. Using English-German IT-domain translation as a case-study, we also enhance the Phrase-based system by exploiting parallel treebanks for syntax-aware phrase extraction and by interfacing with Linked Open Data (LOD) for extracting named entity translations in a post decoding framework.
17
Cuong, Hoang, Khalil Sima’an i Ivan Titov. "Adapting to All Domains at Once: Rewarding Domain Invariance in SMT". Transactions of the Association for Computational Linguistics 4 (grudzień 2016): 99–112. http://dx.doi.org/10.1162/tacl_a_00086.
Pełny tekst źródłaStreszczenie:
Existing work on domain adaptation for statistical machine translation has consistently assumed access to a small sample from the test distribution (target domain) at training time. In practice, however, the target domain may not be known at training time or it may change to match user needs. In such situations, it is natural to push the system to make safer choices, giving higher preference to domain-invariant translations, which work well across domains, over risky domain-specific alternatives. We encode this intuition by (1) inducing latent subdomains from the training data only; (2) introducing features which measure how specialized phrases are to individual induced sub-domains; (3) estimating feature weights on out-of-domain data (rather than on the target domain). We conduct experiments on three language pairs and a number of different domains. We observe consistent improvements over a baseline which does not explicitly reward domain invariance.
18
Neupane, Nabaraj. "CULTURAL TRANSLATION OF PROVERBS FROM NEPALI INTO ENGLISH". LLT Journal: A Journal on Language and Language Teaching 24, nr 2 (29.10.2021): 299–308. http://dx.doi.org/10.24071/llt.v24i2.3045.
Pełny tekst źródłaStreszczenie:
Proverbs are witty, pithy, and epigrammatic expressions. They are idiosyncratic, being based on a specific culture. As cultural translation is difficult, translation of proverbs is not easy. Yet, translation practices on such genre have been appearing. In such a scenario, some such practices are found in the domain of Nepali into English translations. In this background, the present study aims at reviewing the available models for translating proverbs and recommending one, which can be used for translating Nepali proverbs into English. To achieve the objectives, I collected twenty proverbs purposively from Lall (1991) and Sharma (2000), primarily because I could deal only with twenty in a short period and limited space. By way of qualitative analysis and interpretation and by testing Wilson's (2009) model, I have concluded that the model is applicable for the purpose.
19
Soto, Xabier, Olatz Perez-de-Viñaspre, Gorka Labaka i Maite Oronoz. "Neural machine translation of clinical texts between long distance languages". Journal of the American Medical Informatics Association 26, nr 12 (23.07.2019): 1478–87. http://dx.doi.org/10.1093/jamia/ocz110.
Pełny tekst źródłaStreszczenie:
Abstract Objective To analyze techniques for machine translation of electronic health records (EHRs) between long distance languages, using Basque and Spanish as a reference. We studied distinct configurations of neural machine translation systems and used different methods to overcome the lack of a bilingual corpus of clinical texts or health records in Basque and Spanish. Materials and Methods We trained recurrent neural networks on an out-of-domain corpus with different hyperparameter values. Subsequently, we used the optimal configuration to evaluate machine translation of EHR templates between Basque and Spanish, using manual translations of the Basque templates into Spanish as a standard. We successively added to the training corpus clinical resources, including a Spanish-Basque dictionary derived from resources built for the machine translation of the Spanish edition of SNOMED CT into Basque, artificial sentences in Spanish and Basque derived from frequently occurring relationships in SNOMED CT, and Spanish monolingual EHRs. Apart from calculating bilingual evaluation understudy (BLEU) values, we tested the performance in the clinical domain by human evaluation. Results We achieved slight improvements from our reference system by tuning some hyperparameters using an out-of-domain bilingual corpus, obtaining 10.67 BLEU points for Basque-to-Spanish clinical domain translation. The inclusion of clinical terminology in Spanish and Basque and the application of the back-translation technique on monolingual EHRs significantly improved the performance, obtaining 21.59 BLEU points. This was confirmed by the human evaluation performed by 2 clinicians, ranking our machine translations close to the human translations. Discussion We showed that, even after optimizing the hyperparameters out-of-domain, the inclusion of available resources from the clinical domain and applied methods were beneficial for the described objective, managing to obtain adequate translations of EHR templates. Conclusion We have developed a system which is able to properly translate health record templates from Basque to Spanish without making use of any bilingual corpus of clinical texts or health records.
20
Gong, Rui, Dengxin Dai, Yuhua Chen, Wen Li, Danda Pani Paudel i Luc Van Gool. "Analogical Image Translation for Fog Generation". Proceedings of the AAAI Conference on Artificial Intelligence 35, nr 2 (18.05.2021): 1433–41. http://dx.doi.org/10.1609/aaai.v35i2.16233.
Pełny tekst źródłaStreszczenie:
Image-to-image translation is to map images from a given style to another given style. While exceptionally successful, current methods assume the availability of training images in both source and target domains, which does not always hold in practice. Inspired by humans' reasoning capability of analogy, we propose analogical image translation (AIT) that exploit the concept of gist, for the first time. Given images of two styles in the source domain: A and A', along with images B of the first style in the target domain, learn a model to translate B to B' in the target domain, such that A:A' :: B:B'. AIT is especially useful for translation scenarios in which training data of one style is hard to obtain but training data of the same two styles in another domain is available. For instance, in the case from normal conditions to extreme, rare conditions, obtaining real training images for the latter case is challenging. However, obtaining synthetic data for both cases is relatively easy. In this work, we aim at adding adverse weather effects, more specifically fog, to images taken in clear weather. To circumvent the challenge of collecting real foggy images, AIT learns the gist of translating synthetic clear-weather to foggy images, followed by adding fog effects onto real clear-weather images, without ever seeing any real foggy image. AIT achieves zero-shot image translation capability, whose effectiveness and benefit are demonstrated by the downstream task of semantic foggy scene understanding.
21
Streiter, Oliver, i Leonid L. Iomdin. "Learning Lessons from Bilingual Corpora: Benefits for Machine Translation". International Journal of Corpus Linguistics 5, nr 2 (31.12.2000): 199–230. http://dx.doi.org/10.1075/ijcl.5.2.06str.
Pełny tekst źródłaStreszczenie:
The research described in this paper is rooted in the endeavors to combine the advantages of corpus-based and rule-based MT approaches in order to improve the performance of MT systems—most importantly, the quality of translation. The authors review the ongoing activities in the field and present a case study, which shows how translation knowledge can be drawn from parallel corpora and compiled into the lexicon of a rule-based MT system. These data are obtained with the help of three procedures: (1) identification of hence unknown one-word translations, (2) statistical rating of the known one-word translations, and (3) extraction of new translations of multiword expressions (MWEs) followed by compilation steps which create new rules for the MT engine. As a result, the lexicon is enriched with translation equivalents attested for different subject domains, which facilitates the tuning of the MT system to a specific subject domain and improves the quality and adequacy of translation.
22
Yoshida, Yuji. "Weighted Quasi-Arithmetic Means and the Domain Translations". Journal of Advanced Computational Intelligence and Intelligent Informatics 16, nr 1 (20.01.2012): 148–53. http://dx.doi.org/10.20965/jaciii.2012.p0148.
Pełny tekst źródłaStreszczenie:
The monotonicity of the weighted quasi-arithmetic means is discussed from the viewpoint of utility functions and weighting functions. Observing the indices given by utility functions and weighting functions, we find that these indices give similarmonotonicity for the weighted quasi-arithmetic means, and this paper investigates the reason using the direct domain translation adapted to the weighted quasi-arithmetic means. Further, general domain translations are introduced and they are discussed in relation to these indices. Some examples are given for the domain translations and as a special case the translation invariance is presented, and a lot of examples with various utility functions and weighting functions are shown, and their indices and the translated forms are derived.
23
Schäffner, Christina. "Unknown agents in translated political discourse". Target. International Journal of Translation Studies 24, nr 1 (7.09.2012): 103–25. http://dx.doi.org/10.1075/target.24.1.07sch.
Pełny tekst źródłaStreszczenie:
This article investigates the role of translation and interpreting in political discourse. It illustrates discursive events in the domain of politics and the resulting discourse types, such as jointly produced texts, press conferences and speeches. It shows that methods of Critical Discourse Analysis can be used effectively to reveal translation and interpreting strategies as well as transformations that occur in recontextualisation processes across languages, cultures, and discourse domains, in particular recontextualisation in mass media. It argues that the complexity of translational activities in the field of politics has not yet seen sufficient attention within Translation Studies. The article concludes by outlining a research programme for investigating political discourse in translation.
24
Briva-Iglesias, Vicent, Gokhan Dogru i João Lucas Cavalheiro Camargo. "Large language models "ad referendum": How good are they at machine translation in the legal domain?" MonTI. Monografías de Traducción e Interpretación, nr 16 (31.05.2024): 75–107. http://dx.doi.org/10.6035/monti.2024.16.02.
Pełny tekst źródłaStreszczenie:
This study evaluates the machine translation (MT) quality of two state-of-the-art large language models (LLMs) against a traditional neural machine translation (NMT) system across four language pairs in the legal domain. It combines automatic evaluation metrics (AEMs) and human evaluation (HE) by professional translators to assess translation ranking, fluency and adequacy. The results indicate that while Google Translate generally outperforms LLMs in AEMs, human evaluators rate LLMs, especially GPT-4, comparably or slightly better in terms of producing contextually adequate and fluent translations. This discrepancy suggests LLMs' potential in handling specialized legal terminology and context, highlighting the importance of human evaluation methods in assessing MT quality. The study underscores the evolving capabilities of LLMs in specialized domains and calls for reevaluation of traditional AEMs to better capture the nuances of LLM-generated translations.
25
Huang, Jin-Xia, Kyung-Soon Lee i Young-Kil Kim. "Hybrid Translation with Classification: Revisiting Rule-Based and Neural Machine Translation". Electronics 9, nr 2 (21.01.2020): 201. http://dx.doi.org/10.3390/electronics9020201.
Pełny tekst źródłaStreszczenie:
This paper proposes a hybrid machine-translation system that combines neural machine translation with well-developed rule-based machine translation to utilize the stability of the latter to compensate for the inadequacy of neural machine translation in rare-resource domains. A classifier is introduced to predict which translation from the two systems is more reliable. We explore a set of features that reflect the reliability of translation and its process, and training data is automatically expanded with a small, human-labeled dataset to solve the insufficient-data problem. A series of experiments shows that the hybrid system’s translation accuracy is improved, especially in out-of-domain translations, and classification accuracy is greatly improved when using the proposed features and the automatically constructed training set. A comparison between feature- and text-based classification is also performed, and the results show that the feature-based model achieves better classification accuracy, even when compared to neural network text classifiers.
26
Wolk, Krzysztof, i Krzysztof P. Marasek. "Translation of Medical Texts using Neural Networks". International Journal of Reliable and Quality E-Healthcare 5, nr 4 (październik 2016): 51–66. http://dx.doi.org/10.4018/ijrqeh.2016100104.
Pełny tekst źródłaStreszczenie:
The quality of machine translation is rapidly evolving. Today one can find several machine translation systems on the web that provide reasonable translations, although the systems are not perfect. In some specific domains, the quality may decrease. A recently proposed approach to this domain is neural machine translation. It aims at building a jointly-tuned single neural network that maximizes translation performance, a very different approach from traditional statistical machine translation. Recently proposed neural machine translation models often belong to the encoder-decoder family in which a source sentence is encoded into a fixed length vector that is, in turn, decoded to generate a translation. The present research examines the effects of different training methods on a Polish-English Machine Translation system used for medical data. The European Medicines Agency parallel text corpus was used as the basis for training of neural and statistical network-based translation systems. A comparison and implementation of a medical translator is the main focus of our experiments.
27
AYADA, AMINE. "Exploring Scientific Jargon: Diverse Translation Theories for Conveying Computer Scientific Terms into Arabic". ATRAS journal 5, nr 02 (15.07.2024): 77–89. http://dx.doi.org/10.70091/atras/vol05no2.6.
Pełny tekst źródłaStreszczenie:
Translating computer scientific terms into Arabic represents a challenge that necessitates not only linguistic expertise but also a nuanced understanding of both source and target languages. Despite the increasing demand for accurate scientific translation in Arabic-speaking communities, the process is far from being simple. This study embarks on an exploration of scientific translation with a particular focus on computer scientific terms. It aims to identify the challenges encountered by translators and check if the application of translation theories is practical for creating new terms in Arabic. The study is significant as it addresses the pressing need for accurate scientific translation into Arabic language which contributes to the enhancement of communication and knowledge dissemination. An examination of various translation strategies helped to uncover the applicability of translation theories in this context. By scrutinizing the linguistic nuances, we seek to unravel the complexities inherent in translating computer scientific terms into Arabic. Findings not only shed light on the practical application of translation theories but also underscore the importance of context and domain-specific knowledge in achieving accurate and sensitive translations. Ultimately, this study contributes to the broader discourse on scientific translation by offering recommendations for enhancing the precision and fluency of computer scientific translation into Arabic, thereby facilitating the seamless exchange of knowledge across linguistic boundaries.
28
Li, Bin, i Jianmin Yao. "Selection of In-Domain Bilingual Sentence Pairs Based on Topic Information". Scientific Programming 2020 (15.12.2020): 1–7. http://dx.doi.org/10.1155/2020/8879570.
Pełny tekst źródłaStreszczenie:
The performance of a machine translation system (MTS) depends on the quality and size of the training data. How to extend the training dataset for the MTS in specific domains with effective methods to enhance the performance of machine translation needs to be explored. A method for selecting in-domain bilingual sentence pairs based on the topic information is proposed. With the aid of the topic relevance of the bilingual sentence pairs to the target domain, subsets of sentence pairs related to the texts to be translated are selected from a large-scale bilingual corpus to train the translation system in specific domains to improve the translation quality for in-domain texts. Through the test, the bilingual sentence pairs are selected by using the proposed method, and further the MTS is trained. In this way, the translation performance is greatly enhanced.
29
Wang, Huidong, Anna Iacoangeli, Daisy Lin, Keith Williams, Robert B. Denman, Christopher U. T. Hellen i Henri Tiedge. "Dendritic BC1 RNA in translational control mechanisms". Journal of Cell Biology 171, nr 5 (5.12.2005): 811–21. http://dx.doi.org/10.1083/jcb.200506006.
Pełny tekst źródłaStreszczenie:
Translational control at the synapse is thought to be a key determinant of neuronal plasticity. How is such control implemented? We report that small untranslated BC1 RNA is a specific effector of translational control both in vitro and in vivo. BC1 RNA, expressed in neurons and germ cells, inhibits a rate-limiting step in the assembly of translation initiation complexes. A translational repression element is contained within the unique 3′ domain of BC1 RNA. Interactions of this domain with eukaryotic initiation factor 4A and poly(A) binding protein mediate repression, indicating that the 3′ BC1 domain targets a functional interaction between these factors. In contrast, interactions of BC1 RNA with the fragile X mental retardation protein could not be documented. Thus, BC1 RNA modulates translation-dependent processes in neurons and germs cells by directly interacting with translation initiation factors.
30
Müller, Marius, Philipp Schuster, Jonathan Immanuel Brachthäuser i Klaus Ostermann. "Back to Direct Style: Typed and Tight". Proceedings of the ACM on Programming Languages 7, OOPSLA1 (6.04.2023): 848–75. http://dx.doi.org/10.1145/3586056.
Pełny tekst źródłaStreszczenie:
Translating programs into continuation-passing style is a well-studied tool to explicitly deal with the control structure of programs. This is useful, for example, for compilation. In a typed setting, there also is a logical interpretation of such a translation as an embedding of classical logic into intuitionistic logic. A naturally arising question is whether there is an inverse translation back to direct style. The answer to this question depends on how the continuation-passing translation is defined and on the domain of the inverse translation. In general, translating programs from continuation-passing style back to direct style requires the use of control operators to account for the use of continuations in non-trivial ways. We present two languages, one in direct style and one in continuation-passing style. Both languages are typed and equipped with an abstract machine semantics. Moreover, both languages allow for non-trivial control flow. We further present a translation to continuation-passing style and a translation back to direct style. We show that both translations are type-preserving and also preserve semantics in a very precise way giving an operational correspondence between the two languages. Moreover, we show that the compositions of the translations are well-behaved. In particular, they are syntactic one-sided inverses on the full language and full syntactic inverses when restricted to trivial control flow.
31
Yue, Haixiao, Keyao Wang, Guosheng Zhang, Haocheng Feng, Junyu Han, Errui Ding i Jingdong Wang. "Cyclically Disentangled Feature Translation for Face Anti-spoofing". Proceedings of the AAAI Conference on Artificial Intelligence 37, nr 3 (26.06.2023): 3358–66. http://dx.doi.org/10.1609/aaai.v37i3.25443.
Pełny tekst źródłaStreszczenie:
Current domain adaptation methods for face anti-spoofing leverage labeled source domain data and unlabeled target domain data to obtain a promising generalizable decision boundary. However, it is usually difficult for these methods to achieve a perfect domain-invariant liveness feature disentanglement, which may degrade the final classification performance by domain differences in illumination, face category, spoof type, etc. In this work, we tackle cross-scenario face anti-spoofing by proposing a novel domain adaptation method called cyclically disentangled feature translation network (CDFTN). Specifically, CDFTN generates pseudo-labeled samples that possess: 1) source domain-invariant liveness features and 2) target domain-specific content features, which are disentangled through domain adversarial training. A robust classifier is trained based on the synthetic pseudo-labeled images under the supervision of source domain labels. We further extend CDFTN for multi-target domain adaptation by leveraging data from more unlabeled target domains. Extensive experiments on several public datasets demonstrate that our proposed approach significantly outperforms the state of the art. Code and models are available at https://github.com/vis-face/CDFTN.
32
Annoni, Jean-Marie, Hannelore Lee-Jahnke i Annegret Sturm. "Neurocognitive Aspects of Translation". La traduction : formation, compétences, recherches 57, nr 1 (10.10.2012): 96–107. http://dx.doi.org/10.7202/1012743ar.
Pełny tekst źródłaStreszczenie:
Translation is at the centre of many cognitive domains such as pedagogy, linguistic, pragmatic, neurosciences, and social cognition. This multi-domain aspect is reflected in the current models of translation. Recently, cognitive neurosciences have unraveled some brain mechanisms in the bilingualism domain, and it is quite logical to transfer such knowledge to the field of translation as well as the learning of translation. One interesting question is which non-linguistic cognitive and communicative processes are particularly involved in translation. Particularly, in translation, the author’s intentions have to be interpreted although they may not be explicitly stated in the text. These intentions have to be considered while rendering the text for the target public, a process for which it is also important to anticipate the target public’s prior knowledge of the subject and the extent to which the author’s aims and intentions have to be adapted in order to be correctly communicated in the other language. In neuroscience, being able to imagine another person’s mental state is known as having a Theory of Mind (ToM). This skill seems dissociated from the group of executive functions – though it is very dependent on the latter – and seems to rely on a large but individualized brain network. While translation is a widely investigated phenomenon at the micro-level, there is scarcely any research about the process of interpretation going on at the macro-level of text interpretation and rendering. Preliminary neuroscience experiments on the translations paradigm suggest that neurosciences can bring interesting data not only to linguistic but also to cognitive and social mechanisms of translation strategies.
33
Ma, Tianxiang, Bingchuan Li, Wei Liu, Miao Hua, Jing Dong i Tieniu Tan. "CFFT-GAN: Cross-Domain Feature Fusion Transformer for Exemplar-Based Image Translation". Proceedings of the AAAI Conference on Artificial Intelligence 37, nr 2 (26.06.2023): 1887–95. http://dx.doi.org/10.1609/aaai.v37i2.25279.
Pełny tekst źródłaStreszczenie:
Exemplar-based image translation refers to the task of generating images with the desired style, while conditioning on certain input image. Most of the current methods learn the correspondence between two input domains and lack the mining of information within the domain. In this paper, we propose a more general learning approach by considering two domain features as a whole and learning both inter-domain correspondence and intra-domain potential information interactions. Specifically, we propose a Cross-domain Feature Fusion Transformer (CFFT) to learn inter- and intra-domain feature fusion. Based on CFFT, the proposed CFFT-GAN works well on exemplar-based image translation. Moreover, CFFT-GAN is able to decouple and fuse features from multiple domains by cascading CFFT modules. We conduct rich quantitative and qualitative experiments on several image translation tasks, and the results demonstrate the superiority of our approach compared to state-of-the-art methods. Ablation studies show the importance of our proposed CFFT. Application experimental results reflect the potential of our method.
34
Nakagawa, Hiroshi. "Disambiguation of single noun translations extracted from bilingual comparable corpora". Terminology 7, nr 1 (7.12.2001): 63–83. http://dx.doi.org/10.1075/term.7.1.06nak.
Pełny tekst źródłaStreszczenie:
Bilingual machine readable dictionaries are important and indispensable resources of information for cross-language information retrieval, and machine translation. Recently, these cross-language informational activities have begun to focus on specific academic or technological domains. In this paper, we describe a bilingual dictionary acquisition system which extracts translations from non-parallel but comparable corpora of a specific academic domain and disambiguates the extracted translations. The proposed method is two-fold. At the first stage, candidate terms are extracted from a Japanese and English corpus, respectively, and ranked according to their importance as terms. At the second stage, ambiguous translations are resolved by selecting the target language translation which is the nearest in rank to the source language term. Finally, we evaluate the proposed method in an experiment.
35
Irvine, Ann, John Morgan, Marine Carpuat, Hal Daumé i Dragos Munteanu. "Measuring Machine Translation Errors in New Domains". Transactions of the Association for Computational Linguistics 1 (grudzień 2013): 429–40. http://dx.doi.org/10.1162/tacl_a_00239.
Pełny tekst źródłaStreszczenie:
We develop two techniques for analyzing the effect of porting a machine translation system to a new domain. One is a macro-level analysis that measures how domain shift affects corpus-level evaluation; the second is a micro-level analysis for word-level errors. We apply these methods to understand what happens when a Parliament-trained phrase-based machine translation system is applied in four very different domains: news, medical texts, scientific articles and movie subtitles. We present quantitative and qualitative experiments that highlight opportunities for future research in domain adaptation for machine translation.
36
Xie, Jianwen, Zilong Zheng, Xiaolin Fang, Song-Chun Zhu i Ying Nian Wu. "Learning Cycle-Consistent Cooperative Networks via Alternating MCMC Teaching for Unsupervised Cross-Domain Translation". Proceedings of the AAAI Conference on Artificial Intelligence 35, nr 12 (18.05.2021): 10430–40. http://dx.doi.org/10.1609/aaai.v35i12.17249.
Pełny tekst źródłaStreszczenie:
This paper studies the unsupervised cross-domain translation problem by proposing a generative framework, in which the probability distribution of each domain is represented by a generative cooperative network that consists of an energy-based model and a latent variable model. The use of generative cooperative network enables maximum likelihood learning of the domain model by MCMC teaching, where the energy-based model seeks to fit the data distribution of domain and distills its knowledge to the latent variable model via MCMC. Specifically, in the MCMC teaching process, the latent variable model parameterized by an encoder-decoder maps examples from the source domain to the target domain, while the energy-based model further refines the mapped results by Langevin revision such that the revised results match to the examples in the target domain in terms of the statistical properties, which are defined by the learned energy function. For the purpose of building up a correspondence between two unpaired domains, the proposed framework simultaneously learns a pair of cooperative networks with cycle consistency, accounting for a two-way translation between two domains, by alternating MCMC teaching. Experiments show that the proposed framework is useful for unsupervised image-to-image translation and unpaired image sequence translation.
37
Xiao, Ming, Yan Bai, Hui Xu, Xiaolu Geng, Jun Chen, Yujing Wang, Jiakuan Chen i Bo Li. "Effect of NS3 and NS5B proteins on classical swine fever virus internal ribosome entry site-mediated translation and its host cellular translation". Journal of General Virology 89, nr 4 (1.04.2008): 994–99. http://dx.doi.org/10.1099/vir.0.83341-0.
Pełny tekst źródłaStreszczenie:
A full-length NS3 (NS3F) and a truncated NS3 protein (NS3H) with an RNA helicase domain possess RNA helicase activity. Using an in vitro system with a monocistronic reporter RNA or DNA, containing the CSFV 5′-UTR, we observed that both NS3F and NS3H enhanced internal ribosome entry site (IRES)-mediated and cellular translation in a dose-dependent manner, but NS3 protease (NS3P) that lacks a helicase domain did not. NS3F was stronger than NS3H in promoting both translations. These results showed that viral RNA helicase could promote viral and cellular translation, and higher RNA helicase activity might be more efficient. The NS5B protein, the viral replicase, did not significantly affect the IRES-directed or cellular translation alone. NS5B significantly enhanced the stimulative effect of NS3F on both IRES-mediated and cellular translation, but did not affect that of NS3H or NS3P. This suggests that NS5B and NS3 interact via the protease domain during the enhancement of translation.
38
Li, Tianyao. "Exploring Failures and Possible Remedies in AI and Human Translation of English Idioms". Transactions on Social Science, Education and Humanities Research 11 (20.08.2024): 721–28. http://dx.doi.org/10.62051/199nqb23.
Pełny tekst źródłaStreszczenie:
This paper explores the characteristics, similarities and differences between Chinese EFL students and AI when translating English idioms into Chinese. Based on the data collected from the questionnaire on English idioms in English-Chinese translation by Chinese EFL students and AIs, the distribution of human and AI translation accuracies and the focus of translation were analysed using the stereotyped heterogeneous ratio. The results of the survey showed these points: the overall accuracy of translations of Chinese EFL students is lower than that of AI, and the distribution of human translation accuracy among all categories of English idiom was similar to AI translation accuracy; Chinese EFL students tend to retain the form of the proverbs, while AI translators tend to translate the exact meaning; and AI is not able to fully utilise the context to facilitate the understanding of proverbs in the same way as human beings do. Based on the results, this paper expects to provide a reference for future research in this domain.
39
Zhan, Runzhe, Xuebo Liu, Derek F. Wong i Lidia S. Chao. "Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translation". Proceedings of the AAAI Conference on Artificial Intelligence 35, nr 16 (18.05.2021): 14310–18. http://dx.doi.org/10.1609/aaai.v35i16.17683.
Pełny tekst źródłaStreszczenie:
Meta-learning has been sufficiently validated to be beneficial for low-resource neural machine translation (NMT). However, we find that meta-trained NMT fails to improve the translation performance of the domain unseen at the meta-training stage. In this paper, we aim to alleviate this issue by proposing a novel meta-curriculum learning for domain adaptation in NMT. During meta-training, the NMT first learns the similar curricula from each domain to avoid falling into a bad local optimum early, and finally learns the curricula of individualities to improve the model robustness for learning domain-specific knowledge. Experimental results on 10 different low-resource domains show that meta-curriculum learning can improve the translation performance of both familiar and unfamiliar domains. All the codes and data are freely available at https://github.com/NLP2CT/Meta-Curriculum.
40
Guo, Junfei, Juan Liu, Qi Han, Xianlong Chen i Yi Zhao. "Domain mining for machine translation". Journal of Intelligent & Fuzzy Systems 29, nr 6 (14.11.2015): 2769–77. http://dx.doi.org/10.3233/ifs-151981.
Pełny tekst źródła
41
Rao, Minhua. "Translating Metaphors from a Cognitive Perspective: The Case of "Flowers" in Poetry Imagery". International Journal of Social Sciences and Public Administration 4, nr 2 (25.09.2024): 130–35. http://dx.doi.org/10.62051/ijsspa.v4n2.18.
Pełny tekst źródłaStreszczenie:
Imagery is an important element in poetry, the translation of which has traditionally been the main point and difficulty of poetry translation. With the development of cognitive linguistics, cognitive metaphor theory provides a new perspective to study the translation of poetic imagery. Under the perspective of cognitive linguistics, poetic imagery is a conceptual metaphor that maps from the source domain to the target domain, so whether there is a corresponding mapping relationship between two cultures determines how to translate poetic imagery. Flowers are an important creative theme in classical poetry. The translation of flower imagery in ancient Chinese poetry is studied from the perspective of cognitive metaphor theory, and four methods of translating poetic imagery are summarized: direct translation, conversion of vehicle, direct translation with explanation, and translation of meaning without vehicle. These four methods aims at providing reference for the translation of poetic imagery and spreading traditional Chinese culture.
42
BARMAN, S., A. GANGULY i A. BARMAN. "CONFIGURATION AND POLARIZATION DEPENDENT TRANSVERSE DOMAIN WALL MOTION AND DOMAIN WALL SWITCHING IN FERROMAGNETIC NANOWIRE". SPIN 03, nr 01 (marzec 2013): 1350001. http://dx.doi.org/10.1142/s201032471350001x.
Pełny tekst źródłaStreszczenie:
We report that the current induced translational motion of transverse domain wall and domain wall switching in ferromagnetic nanowire is primarily governed by the configuration and polarization of the domain wall. The out-of-plane torque due to nonadiabacity and spin relaxation is found to be the dominant mechanism in the configuration and polarization dependent translational motion of the domain wall. The transverse domain wall undergoes a damped periodic back and forth translational motion along with a periodic switching from +ve polarization to -ve polarization and vice versa under the application of a pulsed current. The domain wall switching occurs at the start of each period of translation.
43
Wang, Yong, Longyue Wang, Shuming Shi, Victor O. K. Li i Zhaopeng Tu. "Go From the General to the Particular: Multi-Domain Translation with Domain Transformation Networks". Proceedings of the AAAI Conference on Artificial Intelligence 34, nr 05 (3.04.2020): 9233–41. http://dx.doi.org/10.1609/aaai.v34i05.6461.
Pełny tekst źródłaStreszczenie:
The key challenge of multi-domain translation lies in simultaneously encoding both the general knowledge shared across domains and the particular knowledge distinctive to each domain in a unified model. Previous work shows that the standard neural machine translation (NMT) model, trained on mixed-domain data, generally captures the general knowledge, but misses the domain-specific knowledge. In response to this problem, we augment NMT model with additional domain transformation networks to transform the general representations to domain-specific representations, which are subsequently fed to the NMT decoder. To guarantee the knowledge transformation, we also propose two complementary supervision signals by leveraging the power of knowledge distillation and adversarial learning. Experimental results on several language pairs, covering both balanced and unbalanced multi-domain translation, demonstrate the effectiveness and universality of the proposed approach. Encouragingly, the proposed unified model achieves comparable results with the fine-tuning approach that requires multiple models to preserve the particular knowledge. Further analyses reveal that the domain transformation networks successfully capture the domain-specific knowledge as expected.1
44
Fu, Yuanbin, Jiayi Ma i Xiaojie Guo. "Unsupervised Exemplar-Domain Aware Image-to-Image Translation". Entropy 23, nr 5 (2.05.2021): 565. http://dx.doi.org/10.3390/e23050565.
Pełny tekst źródłaStreszczenie:
Image-to-image translation is used to convert an image of a certain style to another of the target style with the original content preserved. A desired translator should be capable of generating diverse results in a controllable many-to-many fashion. To this end, we design a novel deep translator, namely exemplar-domain aware image-to-image translator (EDIT for short). From a logical perspective, the translator needs to perform two main functions, i.e., feature extraction and style transfer. With consideration of logical network partition, the generator of our EDIT comprises of a part of blocks configured by shared parameters, and the rest by varied parameters exported by an exemplar-domain aware parameter network, for explicitly imitating the functionalities of extraction and mapping. The principle behind this is that, for images from multiple domains, the content features can be obtained by an extractor, while (re-)stylization is achieved by mapping the extracted features specifically to different purposes (domains and exemplars). In addition, a discriminator is equipped during the training phase to guarantee the output satisfying the distribution of the target domain. Our EDIT can flexibly and effectively work on multiple domains and arbitrary exemplars in a unified neat model. We conduct experiments to show the efficacy of our design, and reveal its advances over other state-of-the-art methods both quantitatively and qualitatively.
45
Zhao, Hui, Hong Wang, Huihui Liu, Maikun Teng i Xu Li. "Crystallization and preliminary crystallographic studies of the W2 domain ofDrosophila melanogastereukaryotic translation initiation factor 5C domain-containing protein". Acta Crystallographica Section F Structural Biology and Crystallization Communications 68, nr 11 (30.10.2012): 1315–17. http://dx.doi.org/10.1107/s1744309112036512.
Pełny tekst źródłaStreszczenie:
TheDrosophila melanogastereukaryotic translation initiation factor 5C domain-containing protein (ECP) is composed of two independently folded domains which belong to the basic leucine-zipper and W2 domain-containing protein (BZW) family. Based on the sequence similarity between the C-terminal W2 domain of ECP and some eukaryotic translation initiation factors (such as eIF2B∊, eIF4γ, eIF5etc.), ECP has been speculated to participate in the translation initiation process. Structural information on the C-terminal W2 domain of ECP would be helpful in understanding the specific cellular function of this protein. Here, the W2 domain of ECP was expressed and crystallized. Crystals grown by the hanging-drop vapour-diffusion method diffracted to 2.70 Å resolution and belonged to space groupI4, with unit-cell parametersa = b = 81.05,c= 57.44 Å. The Matthews coefficient suggested that there was one molecule per asymmetric unit in the crystal.
46
Varsha, N. J. N., T.LakshmiLikitha, S.SivaSankar, Sk Rabiya Basari, i T. leela Vamsi. "BREAKING LANGUAGE BARRIERS: SMART TRANSFORMER TUNING FOR ACCURATE TRANSLATION". Industrial Engineering Journal 54, nr 03 (2025): 101–9. https://doi.org/10.36893/iej.2025.v54i3.011.
Pełny tekst źródłaStreszczenie:
In today's globalized world, the demand for precise, adaptable, and scalable translation tools is at an all-time high. This project presents an advanced multilingual translation platform optimized for domain-specific and multimodal tasks, harnessing cutting-edge Natural Language Processing (NLP) techniques and the transformative capabilities of Marian MT—a state-of-the-art transformer-based architecture renowned for its efficiency, scalability, and contextual precision.The system supports diverse input formats, including text-to-text, imageto-text, and audio-to-text translations, making it an indispensable solution for specialized domains such as healthcare, law, and academia. To enhance non-textual input processing, the platform incorporates Convolutional Neural Networks (CNNs) for precise feature extraction and superior contextual understanding.By leveraging fine-tuned domain-specific datasets and a feedback-driven continuous improvement mechanism, the system delivers unmatched translation accuracy, adaptability, and scalability. Rigorous evaluations using BLEU, ROUGE, and other performance metrics confirm its superior accuracy and contextual fidelity across diverse languages and input modalities.Designed for inclusivity and user-friendliness, the platform serves a wide range of stakeholders, including individuals, businesses, and organizations. It enhances accessibility, supports global collaboration, and sets a new standard for multilingual translation systems in specialized applications, pushing the boundaries of crosscultural and multimodal communication
47
Lin, Jianxin, Yijun Wang, Zhibo Chen i Tianyu He. "Learning to Transfer: Unsupervised Domain Translation via Meta-Learning". Proceedings of the AAAI Conference on Artificial Intelligence 34, nr 07 (3.04.2020): 11507–14. http://dx.doi.org/10.1609/aaai.v34i07.6816.
Pełny tekst źródłaStreszczenie:
Unsupervised domain translation has recently achieved impressive performance with Generative Adversarial Network (GAN) and sufficient (unpaired) training data. However, existing domain translation frameworks form in a disposable way where the learning experiences are ignored and the obtained model cannot be adapted to a new coming domain. In this work, we take on unsupervised domain translation problems from a meta-learning perspective. We propose a model called Meta-Translation GAN (MT-GAN) to find good initialization of translation models. In the meta-training procedure, MT-GAN is explicitly trained with a primary translation task and a synthesized dual translation task. A cycle-consistency meta-optimization objective is designed to ensure the generalization ability. We demonstrate effectiveness of our model on ten diverse two-domain translation tasks and multiple face identity translation tasks. We show that our proposed approach significantly outperforms the existing domain translation methods when each domain contains no more than ten training samples.
48
Liu, Huajun, Lei Chen, Haigang Sui, Qing Zhu, Dian Lei i Shubo Liu. "Unsupervised multi-domain image translation with domain representation learning". Signal Processing: Image Communication 99 (listopad 2021): 116452. http://dx.doi.org/10.1016/j.image.2021.116452.
Pełny tekst źródła
49
Ali, Hazrat, Emma Nyman, Ulf Näslund i Christer Grönlund. "Translation of atherosclerotic disease features onto healthy carotid ultrasound images using domain-to-domain translation". Biomedical Signal Processing and Control 85 (sierpień 2023): 104886. http://dx.doi.org/10.1016/j.bspc.2023.104886.
Pełny tekst źródła
50
Lin, Che-Tsung, Yen-Yi Wu, Po-Hao Hsu i Shang-Hong Lai. "Multimodal Structure-Consistent Image-to-Image Translation". Proceedings of the AAAI Conference on Artificial Intelligence 34, nr 07 (3.04.2020): 11490–98. http://dx.doi.org/10.1609/aaai.v34i07.6814.
Pełny tekst źródłaStreszczenie:
Unpaired image-to-image translation is proven quite effective in boosting a CNN-based object detector for a different domain by means of data augmentation that can well preserve the image-objects in the translated images. Recently, multimodal GAN (Generative Adversarial Network) models have been proposed and were expected to further boost the detector accuracy by generating a diverse collection of images in the target domain, given only a single/labelled image in the source domain. However, images generated by multimodal GANs would achieve even worse detection accuracy than the ones by a unimodal GAN with better object preservation. In this work, we introduce cycle-structure consistency for generating diverse and structure-preserved translated images across complex domains, such as between day and night, for object detector training. Qualitative results show that our model, Multimodal AugGAN, can generate diverse and realistic images for the target domain. For quantitative comparisons, we evaluate other competing methods and ours by using the generated images to train YOLO, Faster R-CNN and FCN models and prove that our model achieves significant improvement and outperforms other methods on the detection accuracies and the FCN scores. Also, we demonstrate that our model could provide more diverse object appearances in the target domain through comparison on the perceptual distance metric.