Numerical Simulation Technology Study on Automatic Translation of Foreign Language Images Based on Tesseract-ORC

Neuroimaging study of numbers, Chinese words, and English words reading in brain

Two groups of subjects were tested to investigate the effect of language on recall span under different memory preload conditions (two, four, or six digits). Native English-speaking monolinguals in Group 1 recalled 1-, 2-, and 3-syllable English words. Chinese-English bilinguals in Group 2 recalled both English words and 1-, 2-, and 3-syllable Chinese words. Word articulation rates for the English monolinguals and the Chinese-English bilinguals in each language were also obtained. An advantage for 1-syllable words over 2- and 3-syllable words was obtained for both articulation and recall. Whereas the effects of word length on recall were constant for English words in all preload conditions, the effect of word length varied with preload condition for the Chinese words: The advantage for 1-syllable Chinese words was very large when preload was small but diminished as digit preload increased. The notion of the “articulatory loop” alone fails to account for this cross-linguistic difference.

An image-based automatic Arabic translation system

Data point overlap exists in the model translation recognition results of generalized maximum likelihood ratio detection (GLR) algorithm. A fuzzy semantic optimal control intelligent recognition model for English translation based on improved GLR algorithm is proposed. This algorithm is used to create a phrase corpus for marking tens of thousands of English and Chinese words, so that phrases can be searched automatically. The algorithm builds a phrase corpus of about 710,000 Chinese and English words. Phrase structure is constructed through phrase centers. Partial speech recognition results can be obtained. According to the syntactic function of analytic linear list, the ambiguity of Chinese and English structures in part of speech recognition results is corrected. Finally get the content of the identifier on the basis of comprehensive evaluation. The recognition accuracy based on the improved algorithm is more than 95%. The overall score was 92.3. This algorithm overcomes the disadvantages of GLR. Compared with statistical algorithm and dynamic memory algorithm, the algorithm improves the operation speed and processing performance and is more suitable for machine translation tasks. It provides a new idea in the field of machine translation.

Aims: The present study aims to examine the cross-script cognate facilitation effect that cognates have processing advantages over non-cognates and this effect is strong evidence supporting the non-selective access hypothesis for bilinguals. Methodology: By adopting a masked translation priming paradigm, Experiment 1 used 48 Chinese–English cognates (Chinese words) and 48 non-cognates (Chinese words) as primes and their English translation equivalences as targets. Chinese–English bilinguals were instructed to judge whether the target stimuli were real words or not. In Experiment 2, another group of participants took the same lexical decision task as in Experiment 1, except that English–Chinese cognates and non-cognates (English words) served as primes and their Chinese translation equivalences were targets. Data and analysis: Response latency and accuracy data were submitted to a repeated-measures analysis of variance. Findings/conclusions: Experiment 1 showed that Chinese–English cognates (Chinese words) and non-cognates (Chinese words) produced similar priming effect, while Experiment 2 revealed that English–Chinese cognates (English words) generated a significant priming effect, whereas non-cognates (English words) failed to induce any priming effect. Overall, Chinese words did not show cognate advantage, while English words produced a significant cognate facilitation effect. These results might be attributed to different mappings from orthography to phonology in English and Chinese. Opaque mapping from orthography to phonology in Chinese hindered phonological activation and reduced Chinese–English cognate phonological priming effect. However, English–Chinese cognates benefited from transparent mapping from sound to print and thus generated a significant phonological priming effect. Implications of the current findings for bilingual word recognition models were discussed. Originality: The present study is the first to investigate the cross-script cognate facilitation effect by ensuring both the heterogeneity of primes and targets (English and Chinese) and the homogeneity of primes (Chinese or English). The results indicated that the writing systems of the primes constrained the cross-script cognate priming effect.

In order to further improve the intelligent level of English translation system and enhance the accuracy of English machine translation, this paper designs an intelligent English automatic translation system for phrase translation combination. The system includes two parts: machine algorithm and software design. Through semantic feature analysis and phrase translation combination mode, the automatic translation algorithm is optimized, the translation algorithm program is loaded, and the automatic translation system software is designed based on embedded environment. On this basis, the automatic design of translation system is carried out by means of cross compiling and multi thread phrase translation loading. The system test results show that the system has high translation accuracy and good intelligence.KeywordsIntelligent translationTranslation combination of phrasesEnglish translation systemAutomation

This chapter presents an automatic translation system from Spanish language into Spanish Sign Language (LSE) based on the use of grammar and morphology rules in order to ensure its versatility. The system accepts input from spoken or written Spanish and the output corresponds to a representation format adaptable and interpretable by any other system capable of producing animations. The translation of a sentence or phrase is carried out in four steps, each of which is performed by a different module: a morphosyntactic analyzer, a grammatical transformer, a morphological transformer and, finally, a sign generator. The system has been successfully integrated in a 3D animation engine and has been tested with a series of phrases, with very satisfactory results, both in speed and in quality.

The article considers the possibility of translating literary texts from a natural language into a target language using an automatic machine translation system. The author considers the possibilities of biological intelligence in comparison with machine "intelligence", which is a prototype of artificial intelligence. The paper gives an example (based on the game in GO) of the emergence of neural networks that appear as a result of self-learning of automated systems. New types of neural networks create an algorithm that always wins (the game of GO) against a person, even with the title of “world champion”. Studies show that automated translation systems must be taught to recognize lexico-semantic groups that would be based on the linguistic categories of natural language. Another task is to teach the machine to “think” and operate with images, since natural language is closely related to images and, at present, cannot be fully algorithmized. The practical application of automatic translation of poetic works shows that automatic machine translation systems, not possessing a psyche, are not able to translate texts of this type.

This article is devoted to the problem of the main ways of assimilating English words into Chinese: phonetic, semantic and calque are the main methods of assimilation of English words. Which way of loan words is preferable remains a debatable question among the Chinese linguistics. Specifics of hieroglyphic writing of the Chinese language predetermined a number of features of assimilating English neologisms by calque. Currently, a large number of words are assimilated in a mixed way, in addition to the exact translation of an English word or part of a word into Chinese, there is necessarily a hieroglyph or a combination of hieroglyphs that convey the sound of English word or part of an English word. Such sound characters can be found in both the preposition and the postposition of the semantic part of word. A distinctive feature of such hieroglyphic signs is their asemantic character. As for the graphic method, it is not a productive way in Chinese. In recent years, in Chinese language a method that hieroglyphic word synthesized by hieroglyphic signs, digital signs, symbols and English graphemes is actively used. The specific point of this loan words method in Chinese is their function as abbreviations. A separate role is the classifier in terms of assimilation of English new words in Chinese. Adding a classifier to a loan word makes it easier for Chinese speakers to understand. This article also describes the variants of assimilation English loan words in Chinese. The article provides a large number of examples illustrating typical ways of assimilating English neologisms in Chinese.

When English speakers are in the early stages of learning Hindi, formulating sentences in Hindi is often attempted by a verbatim translation of English words to corresponding Hindi words. Due to this reason, they are unable to learn Hindi sentences correctly. We have tried to overcome this problem by use of technology for second language learners. The use of Automatic Speech Recognition, and Machine Translation for second language learning, here learning Hindi by English speaker, has been illustrated by taking English speech as input and translating the given English sentences and words into Hindi and then displaying its equivalent construct in Devanagari script. The interactive system under study displays and speaks the same. It has been observed that a second language can be learnt faster by frequently listening to the vocabulary and sentences of the language. Thus the system furnishes the functionality of speaking the sentence in Hindi once it is represented in Devanagari script. The English sentences and words from the grammar tool books are given as input to the system for experimentation. We have observed that the critical problem encountered while doing so is the translation of English to Hindi. Another problem encountered at times is insertion error for letters (only surfaced). The system cannot translate sentences represented using continuous tense and perfect continuous tense correctly. The overall accuracy of the system, otherwise, is approximately 67% which can help the second language learners in the beginning.

Visual data such as images and videos are easily accessible nowadays, and they play critical roles in many real-world applications like surveillance. This raises a series of technological demands for automatic visual understanding and content summarization, which has guided the research community to move towards a better achievement of such capabilities. Meanwhile, it presents the big challenge of semantic understanding of video content and automatically translating them into human language. When developing such automatic translation systems, one critical issue is how to bridge the gap between low level features and high level semantic information. Furthermore, as a large amount of videos are captured under unconstrained conditions by nonprofessional users, this issue becomes even more serious. Therefore, brand new sets of technologies are required to address these difficulties and narrow the semantic gap effectively. These thoughts drive us to survey the complete state-of-the-art techniques in the visual to text topic. Existing methods, popular datasets, technical difficulties, and promising future directions are discussed systematically. In particular, we classify existing methods by their mechanism to link visual information (including both images and videos) and text descriptions, and emphasize the latest advances on deep learning based approaches. The quantitative evaluations of representative approaches on benchmark dataset are also presented and discussed. Finally, we provide with the promising research directions on this topic.

A sign is something that suggests the presence of a fact, condition, or quality. Signs are everywhere in our lives. They make our lives easier when we are familiar with them. But sometimes they pose problems. For example, a tourist might not be able to understand signs in a foreign country. This paper discusses problems of automatic sign recognition and translation. We present a system capable of capturing images, detecting and recognizing signs, and translating them into a target language. We describe methods for automatic sign extraction and translation. We use a user-centered approach in system development. The approach takes advantage of human intelligence if needed and leverage human capabilities. We are currently working on Chinese sign translation. We have developed a prototype system that can recognize Chinese sign input from a video camera that is a common gadget for a tourist, and translate the signs into English or voice stream. The sign translation, in conjunction with spoken language translation, can help international tourists to overcome language barriers. The technology can also help a visually handicapped person to increase environmental awareness.

Large amounts of information is embedded in the natural scenes. Signs are good examples of objects in natural environments which have rich information content. In this paper, we present our efforts in the automatic sign translation. We describe the challenges in the automatic sign translation and introduce the architecture of our current system for automatic detection and translation of Chinese signs. Two data-driven machine translation methods: Example Based Machine Translation (EBMT) and Statistical Machine Translation (SMT) are compared for the task of translating Chinese signs into English. We report the experimental results of both methods that are trained from a small bilingual sign corpus combined with a bilingual glossary. The experiment results indicate that EBMT generates more correct translations while SMT is better at inferring unseen patterns. We are currently working on developing a multi-engine machine translation system that can incrementally learn from the data and combine the results from EBMT and SMT.

Abstract. This paper presents an intelligent system for automatic bidirectional translation between sign language and spoken language, aimed at facilitating inclusive communication between deaf or hard-of-hearing individuals and hearing persons. The proposed system integrates four core modules: sign language recognition, audiovisual speech recognition, sign language synthesis, and speech synthesis. Developed with a constrained vocabulary of 84 phrases relevant to medical consultations, the system enables translation in both directions—sign-to-speech and speech-to-sign. The architecture leverages state-of-the-art deep learning techniques, including transformer-based models, neural vocoders, and avatar-driven gesture synthesis. Experimental evaluations demonstrate high accuracy in gesture and speech recognition, with strong subjective ratings for the naturalness and intelligibility of synthesized outputs. This work contributes to the advancement of accessible communication technologies and lays the groundwork for future expansion into broader domains and unconstrained dialog scenarios.

Objective: This study is the second of a two-part investigation on lexical effects on bilinguals’ performance on a clinical English word recognition test. Focus is on word-frequency effects using counts provided by four corpora. Design: Frequency of occurrence was obtained for 200 NU-6 words from the Hoosier mental lexicon (HML) and three contemporary corpora, American National Corpora, Hyperspace analogue to language (HAL), and SUBTLEXUS. Correlation analysis was performed between word frequency and error rate. Study sample: Ten monolinguals and 30 bilinguals participated. Bilinguals were further grouped according to their age of English acquisition and length of schooling/working in English. Results: Word frequency significantly affected word recognition in bilinguals who acquired English late and had limited schooling/working in English. When making errors, bilinguals tended to replace the target word with a word of a higher frequency. Overall, the newer corpora outperformed the HML in predicting error rate. Conclusions: Frequency counts provided by contemporary corpora predict bilinguals’ recognition of English monosyllabic words. Word frequency also helps explain top replacement words for misrecognized targets. Word-frequency effects are especially prominent for bilinguals foreign born and educated.