Neural Machine Translation of Spanish-English Food Recipes Using LSTM

Dedes, Khen; Utama, Agung Bella Putra; Wibawa, Aji Prasetya; Afandi, Arif Nur; Handayani, Anik Nur; Hernandez, Leonel

doi:10.30630/joiv.6.2.804

Cited by 8 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A unidirectional translation from Kannada to English with neural machine translation has been established by Nagaraj et al 15 the paper received the highest BLEU score of 17.3815. Dedes et al 16 the models proposed with the applied Long Short-Term Memory Method. It has worked with 47 bilingual food recipes between Spanish-English and English-Spanish.…”

Section: Discussionmentioning

confidence: 99%

A Neural Machine Translation Approach for Translating Different Languages in English

Suha,

Khan,

Hossain

2023

Trends Appl. Sci. Res

View full text Add to dashboard Cite

Background and Objective: Neural Machine Translation (NMT) is capable of predicting the likely consequences of a given string of words. Twenty-seven languages were used in the study and by using these 27 language datasets, the model translation capacity has been evaluated. Some sentences of every language compared with the output of Google Translate. Materials and Methods: A recurrent neural network named long short-term memory has been used. Here, the ADAM optimization algorithm and Soft Max Activation function have been used. The BLEU (Bilingual Evaluation Understudy) is used for evaluating translation quality. Results: The research has shown that Western languages have given better BLEU (Bilingual Evaluation Understudy) scores than Asian languages. Especially the Latin script languages have given better translation quality than other script languages. Among 27 languages, the research has worked with four languages whose translations even do not add the Google translator. The translation quality is good according to the BLEU score matrix algorithm. The established neural machine translation system has given a good translation in these aspects. Conclusion: So, in this research, 27 languages are translated into English by the Neural Machine Translation model. The research can contribute to the field of machine translation.

show abstract

Section: Discussionmentioning

confidence: 99%

A Neural Machine Translation Approach for Translating Different Languages in English

Suha,

Khan,

Hossain

2023

Trends Appl. Sci. Res

View full text Add to dashboard Cite

show abstract

“…Today, NMT is the dominant approach in the field of machine translation. NMT, designed to significantly depend on the use of encoders and decoders, is a translation system that uses a completely automated neural network [25]. Instead of translating individual words separately, NMT achieves a higher level of accuracy by taking into account the surrounding context in which the words are utilized.…”

Section: B Machine Translationmentioning

confidence: 99%

Towards Yoruba-Speaking Google Maps Navigation

Oyesanmi,

Olukanmi

2024

Preprint

View full text Add to dashboard Cite

Advances in natural language processing (NLP) have made several technological interventions and services available to people in different languages. One such service is the Google Maps direction narration which provides real-time oral assistance to tourists, and visitors in a new or unknown location. Like most related assistive technologies, this service is primarily developed in the English language with support for some other Western languages over time, and the African languages are largely neglected. This paper seeks to leverage advances in NLP techniques and models in the design of a speech-to-speech (STS) translation of the Google Maps direction narration in English to the Yoruba language, one of the most widely spoken languages in Western Africa. We begin with an exploration of various state-of-the-art NLP techniques for Automatic Speech Recognition (ASR), Machine Translation (MT), and Text-to-speech (TTS) models that make up the designed system. We presented the performance of the models we explored towards the design and implementation of a robust STS translation of the Google Maps direction narration in the Yoruba language.

show abstract

“…Then this study do text processing manually for each dataset, combining the two datasets into one .txt format and then doing text processing automatically using Python to remove non-printable chars, punctuation, and numerical tokens and convert them to lowercase. After the dataset cleaning process, the training and testing process uses the NMT model [20] for the best accuracy for translating Madurese to Indonesian.…”

Section: Figure 1 Design Of the Madurese-indonesian Machine Translati...mentioning

confidence: 99%

LSTM-Based Machine Translation for Madurese-Indonesian

Sulistyo

2023

J. Appl. Data Sci.

View full text Add to dashboard Cite

Madurese is one of the regional languages in Indonesia, which dominates East Java and Madura Island in particular. The use of Madurese as a daily language has declined significantly due to a language shift in children and adolescents, some of which are caused by a sense of prestige and difficulty in learning Madurese. The scarcity of research or scientific titles that raises the Madurese language also helps reduce literacy in the language. Our research focuses on creating a translation machine for Madurese to Indonesian to maintain and preserve the existence of the Madurese language so that learning can be done through digital media. This study use the latest dataset for the Madurese-Indonesian language by using a corpus of 30,000 Madura-Indonesian sentence pairs from the online Bible. This study scrapped online Bible pages to organize the corpus based on the Indonesian and Madurese bilingual Bible. Then This study manually process text to match the two languages' scrapping results, normalization, and tokenization to remove non-printable characters and punctuation from the corpus. To perform neural machine translation (NMT), This study connected the RNN encoder with the RNN decoder of the language model, while for training and testing, This study used a sequential model with LSTM, while the BLEU measure was used to assess the accuracy of the translation results. This study used the SoftMax optimization function with Adam Optimizer and added some settings, including using 128 layers in the training process and adding a Dropout layer so that This study got the average evaluation result for BLEU-1 is 0.798068, BLEU-2 is 0.680932, BLEU-3 is 0.623489, and for BLEU-4 is 0.523546 from five tests conducted. Given the language differences between Madurese and Indonesian, this can be the best approach for machine translation of Indonesian to Madurese.

show abstract

Neural Machine Translation of Spanish-English Food Recipes Using LSTM

Cited by 8 publications

References 29 publications

A Neural Machine Translation Approach for Translating Different Languages in English

A Neural Machine Translation Approach for Translating Different Languages in English

Towards Yoruba-Speaking Google Maps Navigation

LSTM-Based Machine Translation for Madurese-Indonesian

Contact Info

Product

Resources

About