Towards achieving a delicate blending between rule-based translator and neural machine translator

Islam, Md. Adnanul; Anik, Md. Saidul Hoque; Islam, A. B. M. Alim Al

doi:10.1007/s00521-021-05895-x

Cited by 17 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Third, the current study focuses on human translation. Considering the recent success of neural machine translation ( Almansor and Al-Ani, 2018 ; Islam et al, 2021 ), it will contribute further to translation performance research if different task types (i.e., human translation, and post-editing of neural machine translation) are taken into account. Future studies could diversify the design of task features (e.g., task type) and select participants with different language pairs and diverse education backgrounds, so as to explore further the relationships between variables in task complexity, learner factors, and translation performance with larger samples.…”

Section: Discussionmentioning

confidence: 99%

“…The two raters were first invited to get familiar with the assessment guidelines and then worked together to negotiate quality assessment in the marking process. Previous studies revealed that even precise guidelines were given, cognitive bias and disagreement might still occur during the assessment process (Eickhoff, 2018;Islam et al, 2022). The negotiation approach has been widely adopted in writing assessment research and proved as an effective way to reduce raters' bias (Trace et al, 2015).…”

Section: Quality Assessment Metricsmentioning

confidence: 99%

See 1 more Smart Citation

The impact of task complexity and translating self-efficacy belief on students’ translation performance: Evidence from process and product data

2022

View full text Add to dashboard Cite

Previous studies that explored the impact of task-related variables on translation performance focused on task complexity but reported inconsistent findings. This study shows that, to understand the effect of task complexity on translation process and its end product, performance in translation tasks of various complexity levels needs to be compared in a specific setting, in which more factors are considered besides task complexity—especially students’ translating self-efficacy belief (TSEB). Data obtained from screen recording, subjective rating, semi-structured interview, and quality evaluation were triangulated to measure how task complexity influenced the translation performance of Chinese students with high and low TSEB. We found that the complex task led to significantly longer task duration, greater self-reported cognitive effort, lower accuracy, and poorer fluency than the simple one among students, irrespective of their TSEB level. Besides, the high-TSEB group outperformed the low-TSEB group in translation accuracy and fluency in both tasks. However, the interaction effect of task complexity and TSEB was not significant, due possibly to weak problem awareness among students. Our study has implications for effectively designing task complexity, getting the benefits of TSEB, and improving research on translation performance.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Quality Assessment Metricsmentioning

confidence: 99%

The impact of task complexity and translating self-efficacy belief on students’ translation performance: Evidence from process and product data

2022

View full text Add to dashboard Cite

show abstract

“…The most popular machine translation method still needs to perform better on language pairs with low resources compared to their highresource counterparts because no massive parallel corpora are available [11], [12]. Despite the neural machine translation (NMT) success in performance testing, the absence of significant parallel corpora is a practical challenge for many language combinations [14]. Many solutions have been proposed to address this problem, such as triangulation and semi-supervised learning approaches, but they still need a potent cross-lingual signal [15], [16].…”

Section: B Neural Machine Translationmentioning

confidence: 99%

Comparison of Adam Optimization and RMS prop in Minangkabau-Indonesian Bidirectional Translation with Neural Machine Translation

Ahda,

Wibawa,

Dwi Prasetya

et al. 2024

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

Language is a tool humans use to establish communication. Still, the language used is one language and between regions or nations with their languages. Indonesia is a country that has a diversity of second languages and is the fourth most populous country in the world. It is recorded that Indonesia has nearly 800 regional languages, but research activities in natural language processing are still lacking. Minangkabau is an endangered language spoken by the Minangkabau people in Indonesia's West Sumatra province. According to UNESCO, the Minangkabau language is listed as a language that is "definitely endangered," with only around 5 million speakers worldwide. This study uses neural machine translation (NMT) to create a formula based on this information. Neural machine translation, in contrast to conventional statistical machine translation, intends to build a single neural network that can be built up to achieve the best performance. Because it can simultaneously hold memory for a long time, comprehend complicated relationships in data, and provide information that is very important in determining the outcome of translation, LSTM is one of the most powerful machine-learning techniques for translating languages. The BLUE score is utilized in the NMT evaluation. The test results use 520 Minangkabau sentences, conducting tests based on the number of epochs ranging from 100-1000, resulting in optimization using Adam being better than optimization RMSprop. This is evidenced by the results of the best BLUE-1 score of 0.997816 using 1000 epochs.

show abstract

“…Our second finding tells us the capability of MMPLMs in generating a new language pair knowledge space for translating clinical domain text even though this language pair was unseen in the pre-training stage with our experimental settings. This can be useful to low-resource NLP, such as the work by ( 26 , 27 ). 2…”

Section: Introductionmentioning

confidence: 99%

Neural machine translation of clinical text: an empirical investigation into multilingual pre-trained language models and transfer-learning

Han,

Gladkoff,

Erofeev

et al. 2024

Front. Digit. Health

View full text Add to dashboard Cite

Clinical text and documents contain very rich information and knowledge in healthcare, and their processing using state-of-the-art language technology becomes very important for building intelligent systems for supporting healthcare and social good. This processing includes creating language understanding models and translating resources into other natural languages to share domain-specific cross-lingual knowledge. In this work, we conduct investigations on clinical text machine translation by examining multilingual neural network models using deep learning such as Transformer based structures. Furthermore, to address the language resource imbalance issue, we also carry out experiments using a transfer learning methodology based on massive multilingual pre-trained language models (MMPLMs). The experimental results on three sub-tasks including (1) clinical case (CC), (2) clinical terminology (CT), and (3) ontological concept (OC) show that our models achieved top-level performances in the ClinSpEn-2022 shared task on English-Spanish clinical domain data. Furthermore, our expert-based human evaluations demonstrate that the small-sized pre-trained language model (PLM) outperformed the other two extra-large language models by a large margin in the clinical domain fine-tuning, which finding was never reported in the field. Finally, the transfer learning method works well in our experimental setting using the WMT21fb model to accommodate a new language space Spanish that was not seen at the pre-training stage within WMT21fb itself, which deserves more exploitation for clinical knowledge transformation, e.g. to investigate into more languages. These research findings can shed some light on domain-specific machine translation development, especially in clinical and healthcare fields. Further research projects can be carried out based on our work to improve healthcare text analytics and knowledge transformation. Our data is openly available for research purposes at: https://github.com/HECTA-UoM/ClinicalNMT.

show abstract

Towards achieving a delicate blending between rule-based translator and neural machine translator

Cited by 17 publications

References 24 publications

The impact of task complexity and translating self-efficacy belief on students’ translation performance: Evidence from process and product data

The impact of task complexity and translating self-efficacy belief on students’ translation performance: Evidence from process and product data

Comparison of Adam Optimization and RMS prop in Minangkabau-Indonesian Bidirectional Translation with Neural Machine Translation

Neural machine translation of clinical text: an empirical investigation into multilingual pre-trained language models and transfer-learning

Contact Info

Product

Resources

About