The Task of the Human-Machine Translator: Scaling Intelligence and Preserving Transcendence.

A number of Neural Machine Translation (NMT) systems have already demonstrated their strength to undertake various translation tasks which are not too demanding. However, the incredible advancement of AI technology in recent years has endowed Large Language Models (LLMs) with great potential, so we may imagine that they may even do better than NMT working as translators. To figure out whether LLMs have better performance than NMT in translation, and how genres and translation directions may influence translation quality, this article chose two LLMs, namely, ChatGPT 3.5 and Wenxin Yiyan, or ERNIE Bot 3.5, and one NMT system, namely, DeepL, to test and compare their performance in Chinese-English translation, employing a quantitative method including BLEU scoring and SPSS analysis. The results show that there is no significant improvement in these LLMs’ translation quality compared with the NMT system, and all the chosen systems tend to perform better in non-literary translation than in literary translation and produce TTs of higher quality in Chinese-English translation than in English-Chinese translation

Multilingual Neural Translation

Chinese diplomatic discourse plays a crucial role in articulating China’s position and enhancing its influence in global forums. However, machine translation (MT) often struggles with culturally nuanced and abstract expressions, highlighting the need to compare various advanced MT tools. This study assesses and compares the translation quality of Neural Machine Translation (NMT) systems and Large Language Models (LLMs) in translating Chinese diplomatic texts, focusing on the 2025 China-US tariff statements by China’s Foreign Ministry Spokesperson Lin Jian, with <i>China Daily</i>’s official English versions serving as references. Four NMT tools (Niutrans, Youdao, Google, DeepL) and four LLMs (DeepSeek, Ernie-4.5, ChatGPT-4.0, Gemini) were examined. Using the Multidimensional Quality Metrics (MQM) framework, the study evaluated translations, especially for phrases like “奉陪到底” (fight to the end) and “得道多助,失道寡助” (A just cause enjoys abundant support while an unjust one finds little). Results show that LLMs outperform NMTs: 50% of LLMs (DeepSeek, Ernie-4.5) accurately translated both phrases, while only 25% of NMTs (Google) did so for “奉陪到底,” and none for “得道多助,失道寡助.” Both systems faced issues such as undertranslation, omission, and a lack of diplomatic formality. The findings suggest that LLMs have greater potential to handle cultural nuances and abstract content in diplomatic texts, providing insights for enhancing domain-specific MT training and striking a balance between accuracy and acceptability in conveying Chinese diplomatic messages.

Neural Machine Translation (NMT) has presented promising results in Machine translation, convincingly replacing the traditional Statistical Machine Translation (SMT). This success of NMT in machine translation tasks therefore projects to more translation tasks using NMT. This paper systematically reviews the hitherto proposed NMT systems since 2014. 86 NMT papers have been selected and reviewed. The peak of NMT systems were proposed in 2016 and the same was the case for many machine translation workshops who provided datasets for NMT tasks. Most of the proposed systems covered English, German, French and Chinese translation tasks. BLEU score accompanied by significance tests has been seen to be the best metric for NMT systems evaluation. Human judgement for fluency and adequacy is also important to support the metrics. There is still room for further improvement in translations regarding rich source translations and rare words. There is also need for extensive NMT works in other languages to maximize the apparent capabilities of NMT systems. RNN Search and Moses are basically used to develop SMT baselines for model comparisons. Results provide futuristic and directional insights into further translation tasks.

Machine translation, which uses computers to translate one language into another, is one of the most challenging tasks in artificial intelligence. During the last decade, neural machine translation (NMT), which builds translation models based on deep neural networks, has achieved significant improvement. However, NMT still faces several challenges. For example, the translation quality of an NMT system greatly depends on the amount of bilingual training data, which is expensive to acquire. Furthermore, it is difficult to incorporate external knowledge into an NMT system to obtain further improvement for a specific domain. Recently, large language models (LLMs) have demonstrated remarkable capabilities in language understanding and generation. This raises interesting questions about whether LLMs can be good translators and whether it is easy to adapt LLMs to new domains or to meet specific requirements. In this study, we hypothesized that LLMs can be adapted to perform translation by using prompts or fine-tuning and these adapted LLMs would outperform the conventional NMT model in four aspects: translation quality, interactive ability, knowledge incorporation ability, and domain adaptation. We compared GPT-4 and Google Translate, the representative LLM and NMT models, respectively, on the WMT 2019 (Fourth conference on machine translation) dataset. Experimental results showed that GPT-4 outperformed Google Translate in the above four aspects by exploiting appropriate prompts. Further experiments on Llama, an open-source LLM developed by Meta, showed that the translation quality of LLMs can be further improved by fine-tuning on limited language-related bilingual corpus, demonstrating strong adaptation abilities of LLMs.

The rapid global expansion of ChatGPT, which plays a crucial role in interactive knowledge sharing and translation, underscores the importance of comparative performance assessments in artificial intelligence (AI) technology. This study concentrated on this crucial issue by exploring and contrasting the translation performances of large language models (LLMs) and neural machine translation (NMT) systems. For this aim, the APIs of Google Translate, Microsoft Translator, and OpenAI’s ChatGPT were utilized, leveraging parallel corpora from the Workshop on Machine Translation (WMT) 2018 and 2020 benchmarks. By applying recognized evaluation metrics such as BLEU, chrF, and TER, a comprehensive performance analysis across a variety of language pairs, translation directions, and reference token sizes was conducted. The findings reveal that while Google Translate and Microsoft Translator generally surpass ChatGPT in terms of their BLEU, chrF, and TER scores, ChatGPT exhibits superior performance in specific language pairs. Translations from non-English to English consistently yielded better results across all three systems compared with translations from English to non-English. Significantly, an improvement in translation system performance was observed as the token size increased, hinting at the potential benefits of training models on larger token sizes.

This paper introduces the current status of artificial intelligence-based recognition of Chinese characters and machine translation of Chinese characters (Classical Chinese texts), which is currently underway in Korea, and suggests future tasks. For the recognition of Chinese characters, this paper discusses the Chinese character segmentation using the Mask R-CNN algorithm and the Chinese character classification method using the Inception- Resnet-V2 algorithm, and explores the significance and limitations of the construction of Chinese character forms database. Regarding machine translation, this paper looks at the development of machine translation technology from Rule-Based Machine Translation (RBMT) to Neural Machine Translation (NMT); then, introduces the principles of neural network machine translation and techniques applied to improve performance. There are two types of machine translation for Classical Chinese texts: the machine translator provided by Baidu and the translator developed by the Institute for the Translation of Korean Classics (ITKC). Although the Baidu machine translator has various errors, the overall translation performance is somewhat higher than that of ITKC's machine translator. The ITKC's translator performs better than the Baidu translator in certain areas, but falls short of the Baidu translator in translating various types of Classical Chinese texts. In order to improve the performance of the machine translation of Classical Chinese texts, it is necessary tobuild a cloud-based translation platform, expand a high-quality parallel corpus, develop an additional system to improve machine translation performance, and develop a highly reliable translation evaluation method.

Recent work achieved remarkable results in training neural machine translation (NMT) systems in a fully unsupervised way, with new and dedicated architectures that only rely on monolingual corpora. However, previous work also showed that unsupervised statistical machine translation (USMT) performs better than unsupervised NMT (UNMT), especially for distant language pairs. To take advantage of the superiority of USMT over UNMT, and considering that SMT suffers from well-known limitations overcome by NMT, we propose to define UNMT as NMT trained with the supervision of synthetic parallel data generated by USMT. This way we can exploit USMT up to its limits while ultimately relying on full-fledged NMT models to generate translations. We show significant improvements in translation quality over previous work and also that further improvements can be obtained by alternatively and iteratively training USMT and UNMT. Without the need of a dedicated architecture for UNMT, our simple approach can straightforwardly benefit from any recent and future advances in supervised NMT. Our systems achieve a new state-of-the-art for unsupervised machine translation in all of our six translation tasks for five diverse language pairs, surpassing even supervised SMT or NMT in some tasks. Furthermore, our analysis shows how crucial the comparability between the monolingual corpora used for unsupervised training is in improving translation quality.

We address the challenging task of neural machine translation (NMT) in the entertainment domain, where the objective is to automatically translate a given dialogue from a source language content to a target language. This task has various applications, particularly in automatic dubbing, subtitling, and other content localization tasks, enabling source content to reach a wider audience. Traditional NMT systems typically translate individual sentences in isolation, without facilitating knowledge transfer of crucial elements such as the context and style from previously encountered sentences. In this work, we emphasize the significance of these fundamental aspects in producing pertinent and captivating translations. We demonstrate their significance through several examples and propose a novel framework for entertainment translation, which, to our knowledge, is the first of its kind. Furthermore, we introduce an algorithm to estimate the context and style of the current session and use these estimations to generate a prompt that guides a Large Language Model (LLM) to generate high-quality translations. Our method is both language and LLM-agnostic, making it a general-purpose tool. We demonstrate the effectiveness of our algorithm through various numerical studies and observe significant improvement in the COMET scores over various state-of-the-art LLMs. Moreover, our proposed method consistently outperforms baseline LLMs in terms of win-ratio.

Neural machine translation (NMT) has shown promising progress in recent years. However, for reducing the computational complexity, NMT typically needs to limit its vocabulary scale to a fixed or relatively acceptable size, which leads to the problem of rare word and out-of-vocabulary (OOV). In this paper, we present that the semantic concept information of word can help NMT learn better semantic representation of word and improve the translation accuracy. The key idea is to utilize the external semantic knowledge base WordNet to replace rare words and OOVs with their semantic concepts of WordNet synsets. More specifically, we propose two semantic similarity models to obtain the most similar concepts of rare words and OOVs. Experimental results on 4 translation tasks (We verify the effectiveness of our method on four translation tasks, including English-to- German, German-to-English, English-to-Chinese and Chinese-to-English.) show that our method outperforms the baseline RNNSearch by 2.38–2.88 BLEU points. Furthermore, the proposed hybrid method by combining BPE and our proposed method can also gain 0.39–0.97 BLEU points improvement over BPE. Experiments and analysis presented in this study also demonstrate that the proposed method can significantly improve translation quality of OOVs in NMT.

Neural Machine Translation (NMT) has recently achieved the state-of-the-art in many machine translation tasks, but one of the challenges that NMT faces is the lack of parallel corpora, especially for low-resource language pairs. And the result is that the performance of NMT is much less effective for low-resource languages. To address this specific problem, in this paper, we describe a novel NMT model that is based on encoder-decoder architecture and relies on character-level inputs. Our proposed model employs Convolutional Neural Networks (CNN) and highway networks over character inputs, whose outputs are given to an encoder-decoder neural machine translation network. Besides, we also present two other approaches to improve the performance of the low-resource NMT system much further. First, we use language modeling implemented by denoising autoencoding to pre-train and initialize the full model. Second, we share the weights of the front few layers of two encoders between two languages to strengthen the encoding ability of the model. We demonstrate our model on two low-resource language pairs. On the IWSLT2015 English-Vietnamese translation task, our proposed model obtains improvements up to 2.5 BLEU points compared to the baseline. We also outperform the baseline approach more than 3 BLEU points on the CWMT2018 Chinese-Mongolian translation task.

Recently, the neural machine translation systems showed their promising performance and surpassed the phrase-based systems for most translation tasks. Retreating into conventional concepts machine translation while utilizing effective neural models is vital for comprehending the leap accomplished by neural machine translation over phrase-based methods. This work proposes a direct HMM with neural network-based lexicon and alignment models, which are trained jointly using the Baum-Welch algorithm. The direct HMM is applied to rerank the n-best list created by a state-of-the-art phrase-based translation system and it provides improvements by up to 1.0% Bleu scores on two different translation tasks.

The statistical machine translation for the Arabic language integrates external linguistic resources such as part-of-speech tags. The current research presents a Bidirectional Long Short-Term Memory (Bi-LSTM)—Conditional Random Fields (CRF) segment-level Arabic Dialect POS tagger model, which will be integrated into the Multitask Neural Machine Translation (NMT) model. The proposed solution for NMT is based on the recurrent neural network encoder-decoder NMT model that has been introduced recently. The study has proposed and developed a unified Multitask NMT model that shares an encoder between the two tasks; Arabic Dialect (AD) to Modern Standard Arabic (MSA) translation task and the segment-level POS tagging tasks. A shared layer and an invariant layer are shared between the translation tasks. By training translation tasks and POS tagging task alternately, the proposed model can leverage the characteristic information and improve the translation quality from Arabic dialects to Modern Standard Arabic. The experiments are conducted from Levantine Arabic (LA) to MSA and Maghrebi Arabic (MA) to MSA translation tasks. As an additional linguistic resource, the segment-level part-of-speech tags for Arabic dialects were also exploited. Experiments suggest that translation quality and the performance of POS tagger were improved with the implementation of multitask learning approach.

Benefitting from the rapid development of artificial intelligence (AI) and deep learning, the machine translation task based on neural networks has achieved impressive performance in many high-resource language pairs. However, the neural machine translation (NMT) models still struggle in the translation task on agglutinative languages with complex morphology and limited resources. Inspired by the finding that utilizing the source-side linguistic knowledge can further improve the NMT performance, we propose a multi-source neural model that employs two separate encoders to encode the source word sequence and the linguistic feature sequences. Compared with the standard NMT model, we utilize an additional encoder to incorporate the linguistic features of lemma, part-of-speech (POS) tag, and morphological tag by extending the input embedding layer of the encoder. Moreover, we use a serial combination method to integrate the conditional information from the encoders with the outputs of the decoder, which aims to enhance the neural model to learn a high-quality context representation of the source sentence. Experimental results show that our approach is effective for the agglutinative language translation, which achieves the highest improvements of +2.4 BLEU points on Turkish–English translation task and +0.6 BLEU points on Uyghur–Chinese translation task.

The present study presents a comparative analysis of the translation processes and outcomes of human translators, Neural Machine Translation (NMT) systems and Large Language Models (LLMs) focusing on the translation of Metaphor-related Words (MRW). The study employs various research methodologies, including product analysis, think-aloud protocols, subsequent interviews, and translation quality assessments to uncover the choice of strategies in translating MRWs by different subject groups as well as its relation with quality criterion. Human translators and LLMs tend to favour strategies such as metaphor into different metaphor (M-M2) and metaphor reduction (M→Non), while NMT systems prefer the reproduction of metaphors (M→M). LLMs demonstrate translation patterns which are more aligned with human translators, helping them achieve higher evaluation scores, though their performance remains inconsistent, particularly with novel metaphors. Additionally, human translators process metaphors by incorporating conceptual, cultural, and contextual factors, whereas LLMs tend to rely on paraphrastic approaches. Evaluation results indicate that LLMs exhibit proficiency on par with novice translators in terms of accuracy, idiomatic expression, and vividness in metaphor translation, while NMT systems fall slightly short. The study highlights the influence of translation strategies on the quality of metaphor translation and concludes that, while NMT systems and LLMs can achieve performance comparable to human translators, much larger metaphor-specific datasets supported studies are expected to validate its consistency.