Language Translation Tasks Research Articles

Cross-Language Translation and Comparative Study of English Literature Using Machine Translation Algorithms

Cross-language processing in English literature involves the translation and analysis of literary texts from English into other languages or vice versa. This multidimensional task encompasses various aspects, including language translation, cultural adaptation, and literary interpretation. Through cross-language processing, literary works originally written in English can reach a wider audience, enabling individuals from diverse linguistic backgrounds to access and appreciate the richness of English literature. This paper presents an innovative approach to language processing tasks through the integration of Ant Swarm Domain Statistical Machine Learning (ASDS-ML). Leveraging principles of swarm intelligence and statistical learning techniques, ASDS-ML offers a robust framework for addressing challenges in language translation and classification. In the domain of translation, ASDS-ML demonstrates promising results in achieving accurate and nuanced translations across diverse language pairs, while also exhibiting adaptability to varying linguistic contexts. Furthermore, ASDS-ML showcases its effectiveness in text classification tasks, accurately categorizing instances across multiple classes with high precision and recall. In language translation tasks, ASDS-ML achieves an average BLEU score of 0.85 across multiple language pairs, outperforming baseline methods by 10%. Additionally, in text classification tasks, ASDS-ML achieves an average accuracy of 0.92 across ten different classes, surpassing existing approaches by 5%.

The Role of Artificial Intelligence in Facilitating Real-Time Language Translation to Complement ESL Education

Abstract Real-time English translation systems incorporating speech recognition have a wide range of application scenarios due to the need for further language translation support for second language learners in ESL programs. The traditional Transformer model is further improved by this study using the end-to-end speech recognition model for performance enhancement considerations when performing real-time language translation tasks. The study examines the degree to which the real-time language translation system enhances the learning effect of students in ESL courses. It is found that the Transformer model based on the attention mechanism has obvious performance advantages in a large corpus, and the improved Transformer model containing the transcription network module, prediction network module, and cointegration network module has stronger performance in recognizing English speech. In the case study based on five students, the average recognition time of the translation system under the improved Transformer model is 1.2295 seconds, which is 0.8132 seconds faster than that of the traditional Transformer model, proving that it has a better real-time English translation performance. In a controlled experiment of ESL course learning within a school, the average translation score of the students in the experimental group is 90.45±2.91, which is better than the average translation score of the students in the control group, and there is a significant difference in the translation scores between the experimental group and the control group (P<0.001).

Langevin Cooling for Unsupervised Domain Translation.

Domain translation is the task of finding correspondence between two domains. Several deep neural network (DNN) models, e.g., CycleGAN and cross-lingual language models, have shown remarkable successes on this task under the unsupervised setting--the mappings between the domains are learned from two independent sets of training data in both domains (without paired samples). However, those methods typically do not perform well on a significant proportion of test samples. In this article, we hypothesize that many of such unsuccessful samples lie at the fringe--relatively low-density areas--of data distribution, where the DNN was not trained very well, and propose to perform the Langevin dynamics to bring such fringe samples toward high-density areas. We demonstrate qualitatively and quantitatively that our strategy, called Langevin cooling (L-Cool), enhances state-of-the-art methods in image translation and language translation tasks.

Filtering and Extended Vocabulary based Translation for Low-resource Language Pair of Sanskrit-Hindi

Neural Machine Translation (NMT) is widely employed for language translation tasks because it performs better than the conventional statistical and phrase-based approaches. However, NMT techniques involve challenges, such as requiring a large and clean corpus of parallel data and the inability to deal with rare words. They need to be faster for real-time applications. More work needs to be done using NMT to address the challenges in translating Sanskrit, one of the oldest and rich languages known to the world, with its morphological richness and limited multilingual parallel corpus. There is usually no similar data between a language pair; hence, no application exists so far that can translate Sanskrit to/from other languages. This study presents an in-depth analysis to address these challenges with the help of a low-resource Sanskrit-Hindi language pair. We employ a novel training corpus filtering with extended vocabulary in a zero-shot transformer architecture. The structure of the Sanskrit language is thoroughly investigated to justify the use of each step. Furthermore, the proposed method is analyzed based on variations in sentence length and also applied to a high-resource language pair in order to demonstrate its efficacy.

FluentSigners-50: A signer independent benchmark dataset for sign language processing.

This paper presents a new large-scale signer independent dataset for Kazakh-Russian Sign Language (KRSL) for the purposes of Sign Language Processing. We envision it to serve as a new benchmark dataset for performance evaluations of Continuous Sign Language Recognition (CSLR) and Translation (CSLT) tasks. The proposed FluentSigners-50 dataset consists of 173 sentences performed by 50 KRSL signers resulting in 43,250 video samples. Dataset contributors recorded videos in real-life settings on a wide variety of backgrounds using various devices such as smartphones and web cameras. Therefore, distance to the camera, camera angles and aspect ratio, video quality, and frame rates varied for each dataset contributor. Additionally, the proposed dataset contains a high degree of linguistic and inter-signer variability and thus is a better training set for recognizing a real-life sign language. FluentSigners-50 baseline is established using two state-of-the-art methods, Stochastic CSLR and TSPNet. To this end, we carefully prepared three benchmark train-test splits for models' evaluations in terms of: signer independence, age independence, and unseen sentences. FluentSigners-50 is publicly available at https://krslproject.github.io/FluentSigners-50/.

Knowledge Graph and Deep Learning-based Text-to-GQL Model for Intelligent Medical Consultation Chatbot.

Text-to-GraphQL (Text2GraphQL) is a task that converts the user's questions into Graph + QL (Query Language) when a graph database is given. That is a task of semantic parsing that transforms natural language problems into logical expressions, which will bring more efficient direct communication between humans and machines. The existing related work mainly focuses on Text-to-SQL tasks, and there is no available semantic parsing method and data set for the graph database. In order to fill the gaps in this field to serve the medical Human–Robot Interactions (HRI) better, we propose this task and a pipeline solution for the Text2GraphQL task. This solution uses the Adapter pre-trained by “the linking of GraphQL schemas and the corresponding utterances” as an external knowledge introduction plug-in. By inserting the Adapter into the language model, the mapping between logical language and natural language can be introduced faster and more directly to better realize the end-to-end human–machine language translation task. In the study, the proposed Text2GraphQL task model is mainly constructed based on an improved pipeline composed of a Language Model, Pre-trained Adapter plug-in, and Pointer Network. This enables the model to copy objects' tokens from utterances, generate corresponding GraphQL statements for graph database retrieval, and builds an adjustment mechanism to improve the final output. And the experiments have proved that our proposed method has certain competitiveness on the counterpart datasets (Spider, ATIS, GeoQuery, and 39.net) converted from the Text2SQL task, and the proposed method is also practical in medical scenarios.

Functional Connectivity Signatures Underlying Simultaneous Language Translation in Interpreters and Non-Interpreters of Mandarin and English: An fNIRS Study.

Recent neuroimaging research has suggested that interpreters and non-interpreters elicit different brain activation patterns during simultaneous language translation. However, whether these two groups have different functional connectivity during such a task, and how the neural coupling is among brain subregions, are still not well understood. In this study, we recruited Mandarin (L1)/English (L2) interpreters and non-interpreter bilinguals, whom we asked to perform simultaneous language translation and reading tasks. Functional near-infrared spectroscopy (fNIRS) was used to collect cortical brain data for participants during each task, using 68 channels that covered the prefrontal cortex and the bilateral perisylvian regions. Our findings revealed both interpreter and non-interpreter groups recruited the right dorsolateral prefrontal hub when completing the simultaneous language translation tasks. We also found different functional connectivity between the groups. The interpreter group was characterized by information exchange between the frontal cortex and Wernicke’s area. In comparison, the non-interpreter group revealed neural coupling between the frontal cortex and Broca’s area. These findings indicate expertise modulates functional connectivity, possibly because of more developed cognitive skills associated with executive functions in interpreters.

Natural Language Generation and Creative Writing A Systematic Review

Among studies on natural language generation (NLG), computational creativity, and human-computer interaction; there is a vision of witnessing these tools collaborating with humans in generating and authoring creative content. This study aims to systematically review published studies discussing creative writing and story generation during the period of 2016-2021. This work seeks to identify the primary research methods used in NLG and creative writing studies, to locate how these studies are distributed geographically, and finally, to classify the subfields or common keywords primarily used in NLG involving creative writing. The findings suggest that experiment studies and problem-solving were the most common research methods in NLG and creative writing. Major identified themes in the reviewed articles include story generation, language models, and co-creativity, along with some gaps in foreign language translation and humour generation studies. The majority of the studies suggest that NLG tasks had a positive impact on creative writing. Common tasks related to NLG and creative writing are typically using keywords such as story generation, co-creativity, co-writing, user interface and writing tools. In future work, we aim to explore more GPT-3 capabilities in creative writing, in addition to creative writing applications in foreign language translation tasks.

A Deep Learning Approach to Ancient Egyptian Hieroglyphs Classification

Nowadays, advances in Artificial Intelligence (AI), especially in machine and deep learning, present new opportunities to build tools that support the work of specialists in areas apparently far from the information technology field. One example of such areas is that of ancient Egyptian hieroglyphic writing. In this study, we explore the ability of different convolutional neural networks (CNNs) to classify pictures of ancient Egyptian hieroglyphs coming from two different datasets of images. Three well-known CNN architectures (ResNet-50, Inception-v3 and Xception) were taken into consideration and trained on the available images. The paradigm of transfer learning was tested as well. In addition, modifying the architecture of one of the previous networks, we developed a specifically dedicated CNN, named Glyphnet, tailoring its complexity to our classification task. Performance comparison tests were carried out and Glyphnet showed the best performances with respect to the other CNNs. In conclusion, this work shows how the ancient Egyptian hieroglyphs identification task can be supported by the deep learning paradigm, laying the foundation for information tools supporting automatic documents recognition, classification and, most importantly, the language translation task.

A Study on the Intelligent Translation Model for English Incorporating Neural Network Migration Learning

Under the current artificial intelligence boom, machine translation is a research direction of natural language processing, which has important scientific research value and practical value. In practical applications, the variability of language, the limited capability of representing semantic information, and the scarcity of parallel corpus resources all constrain machine translation towards practicality and popularization. In this paper, we conduct deep mining of source language text data to express complex, high‐level, and abstract semantic information using an appropriate text data representation model; then, for machine translation tasks with a large amount of parallel corpus, I use the capability of annotated datasets to build a more effective migration learning‐based end‐to‐end neural network machine translation model on a supervised algorithm; then, for machine translation tasks with parallel corpus data resource‐poor language machine translation tasks, migration learning techniques are used to prevent the overfitting problem of neural networks during training and to improve the generalization ability of end‐to‐end neural network machine translation models under low‐resource conditions. Finally, for language translation tasks where the parallel corpus is extremely scarce but monolingual corpus is sufficient, the research focuses on unsupervised machine translation techniques, which will be a future research trend.

Recognition of radar active‐jamming through convolutional neural networks

Radar application in modern warfare becomes more and more rigorous because of the rapidly developed radar countermeasures, especially active jamming in recent years. It costs a radar many resources for anti-jamming in order to detect a target. Hence, it is of great value to recognise the active jamming and thereafter take measures to distinguish target from the numerous jamming. Traditional methods of recognition jamming are blamed for its low efficiency and low accuracy. Radar researchers are looking forward to a new way to do the recognition work. Machine learning has made great advancements in many areas such as image classification, language translation, signal processing and many other recognition tasks, due to its great performance and high accuracy. The authors applied a machine learning method, i.e. convolutional neural networks, to recognise active jamming here. The authors’ results demonstrate that convolutional neural networks have strong ability to distinguish active jamming and thus provide them adequate preparation for anti-jamming process.

Multi-way, multilingual neural machine translation

We propose multi-way, multilingual neural machine translation. The proposed approach enables a single neural translation model to translate between multiple languages, with a number of parameters that grows only linearly with the number of languages. This is made possible by having a single attention mechanism that is shared across all language pairs. We train the proposed multi-way, multilingual model on ten language pairs from WMT’15 simultaneously and observe clear performance improvements over models trained on only one language pair. We empirically evaluate the proposed model on low-resource language translation tasks. In particular, we observe that the proposed multilingual model outperforms strong conventional statistical machine translation systems on Turkish-English and Uzbek-English by incorporating the resources of other language pairs.

Knowledge Structure Measures of Reader’s Situation Models Across Languages: Translation Engenders Richer Structure

In order to further validate and extend the application of recent knowledge structure (KS) measures to second language settings, this investigation explores how second language (L2, English) situation models are influenced by first language (L1, Korean) translation tasks. Fifty Korean low proficient English language learners were asked to read an L2 story and then complete L2 concept map and summary writing tasks, with or without an intervening L1 production tasks (Translated versus Directed conditions). Posttest comprehension was measured using the TOEFL multiple-choice items associated with the story (both in L2). KS elicited as concept maps and as text summaries were used to represent the situation models before, during, and after writing. For analysis, all of the participants’ maps and writing artifacts were converted into Pathfinder Networks (PFNets) that were analyzed using two distinctly different approaches, correlation of the raw proximity data and also degree centrality of the PFNets, in order to analyze the PFNets statistically and to visually describe KS cognitive state changes over time. The correlation results showed that the Translated Writing participants’ L2 KS relative to the Directed Writing condition are more similar to that of an expert and are significantly correlated with comprehension posttest scores. Including L1 tasks substantially improved the qualities of the L2 KS artifacts and underlying mental structures related to reading comprehension. In addition, the average centrality results showed that the KS ‘form’ of the participants’ PFNets who translated were relational network structures relative to the Directed Writing group’s (English only) PFNets that had a more linear structure that matched the text surface structure, suggesting a fundamental way that L1 and L2 cognitive processing differs.

The effects of textual enhancement type on L2 form recognition and reading comprehension in Spanish

Previous research investigating the effectiveness of textual enhancement as a tool to draw adult second language (L2) learners’ attention to the targeted linguistic form has consistently produced mixed results. This article examines how L2 form recognition and reading comprehension are affected by different types of textual enhancement. Participants ( n = 109) in the experimental group read a passage that contained one type of textual enhancement (underline, bold, italics, change in font size, use of capital letters or change of font) on the target structure (Spanish present and preterit tense) morphemes. A control group ( n = 16) read the same passage without any type of enhancement. To measure L2 form recognition, all groups completed pre- and post-tests consisting of an L2 to first language (L1) translation task. To assess the effects of enhancement type on L2 reading comprehension, the participants completed a 40 item multiple choice test with questions focusing on form or meaning from the reading. Results for the present study revealed that one type of textual enhancement was better than others with regard to facilitating L2 form recognition, and that comprehension was not hindered by enhancement, regardless of enhancement type.

Wolne oprogramowanie dla tłumacza – mit czy rzeczywistość?

The main purpose of this paper is to describe and to review “free software” used for supporting language translation tasks. Comparison with commercial programs gives the answer whether “free software” is a valid alternative solution for translators and what its future development may look like. My definition of “free software”, a very broad one, is based on the availability of programs for translators and embraces categories such as open source, freeware and adware. The focus is not only on consolidated projects as, for instance, OmegaT or PlusTools but also on experimental web-based solutions such as NETS by Adriano Allora. The main part of the paper contains a detailed evaluation of the open source program OmegaT in comparison to Trados (SDL Trados 2007) and illustrates the rules and the mechanisms of Computer Assisted Translation in order to explain frequent misunderstandings that arise among beginner translators. What is particularly emphasized is the deep conceptual and technical difference between Machine Assisted Human Translation and Human Assisted Machine Translation. It is argued that, although open source and centralized web-based translation memories still present some disadvantages as compared to commercial systems, they are already fully functional substitutes for the powerful leading market solutions. The aim of this paper is also to motivate interest in CAT tools among translators so that they could actively take part in the future development of this kind of software as developers, programmers, testers, reviewers or technology-conscious users.

The IXM2 parallel associative processor for AI

Describes the IXM2 associative processor and its main application in speech-to-speech translation. The IXM2 is a semantic memory system machine that began as a faithful implementation of the NETL semantic network machine and grew into a massively parallel SIMD machine that has demonstrated the power of large associative memories. Such processors can support robust performance in speech applications. In fact, the IXM2 with 73 transputers has outperformed a Cray in some language-translation tasks. We selected speech-to-speech translation as our main application because it is one of the grand challenges of massively parallel artificial intelligence. The social implications of successful automatic translation are enormous-e.g. people who speak different languages could communicate in real time by using interpreting telephony. >