TLSPG: Transfer learning-based semi-supervised pseudo-corpus generation approach for zero-shot translation

Kumar, Amit; Mundotiya, Rajesh Kumar; Pratap, Ajay; Singh, Anil Kumar

doi:10.1016/j.jksuci.2022.03.008

Cited by 4 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 2 outlines studies on translation with low-resource languages using pseudoparallel corpora. In their research, Kumar et al [24] explored semi-supervised learning for transfer translation with a pseudo-corpus. They delved into languages such as Bhojpuri, Magahi, Hindi, and Magah, utilizing BLEU, ChrF, and TER for performance assessment.…”

Section: Pseudo-parallel Corporamentioning

confidence: 99%

Automatic Translation between Mixtec to Spanish Languages Using Neural Networks

Santiago-Benito,

Córdova-Esparza,

Castro-Sánchez

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

This paper introduces a novel method for collecting and translating texts from the Mixtec to the Spanish language. The method comprises four primary steps. First, we collected a Mixtec–Spanish corpus that includes 4568 sentences from educational and religious domain texts. To enhance the parallel corpus, we generate synthetic data with GPT-3.5. Second, we cleaned the data with a semi-automatic approach followed by preprocessing and tokenization. In preprocessing, we removed stop words, duplicated sentences, special characters, and numbers and converted them to lowercase. Third, we performed semi-automatic alignment to find the correspondence of Mixtec–Spanish sentences to generate sentence-level aligned texts necessary for translation. Finally, we trained automatic translation models based on recurrent neural networks, bidirectional recurrent neural networks, and Transformers. Our system achieved a BLEU score of 95.66 for Mixtec-to-Spanish translation and 99.87 for Spanish-to-Mixtec translation. We also obtained a translation edit rate (TER) of 0.5 for Spanish-to-Mixtec and a TER of 16.5 for Mixtec-to-Spanish. Our research stands out as a pioneering effort in the field of automatic Mixtec-to-Spanish translation in Mexico, filling a gap identified in the current literature.

show abstract

Section: Pseudo-parallel Corporamentioning

confidence: 99%

Automatic Translation between Mixtec to Spanish Languages Using Neural Networks

Santiago-Benito,

Córdova-Esparza,

Castro-Sánchez

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…For training the model, we use NE↔HI language pairs and use language transfer on zero-shot pairs to evaluate the model on validation datasets. The reason behind using NE↔HI language pairs for training the model in unsupervised experiments on Bhojpuri-Hindi and Magahi-Hindi is the higher similarity between NE↔HI language pairs with both Bhojpuri-Hindi and Magahi-Hindi zero-shot language pairs based on [65].…”

Section: Unsupervised Settingsmentioning

confidence: 99%

Study of Local Site Conditions for Seismic Hazard Assessment at the BHU Campus, Varanasi, North India, using Ambient Noise Measurements

Kumari

Singh

Shankar

et al. 2022

Journal of the Geological Society of India

View full text Add to dashboard Cite

The use of subword embedding has proved to be a major innovation in Neural Machine Translation (NMT). It helps NMT to learn better context vectors for Low Resource Languages (LRLs) so as to predict the target words by better modelling the morphologies of the two languages and also the morphosyntax transfer. Even so, their performance for translation in Indian language to Indian language scenario is still not as good as for resource-rich languages. One reason for this is the relative morphological richness of Indian languages, while another is that most of them fall into the extremely low resource or zero-shot categories. Since most major Indian languages use Indic or Brahmi origin scripts, the text written in them is highly phonetic in nature and phonetically similar in terms of abstract letters and their arrangements. We use these characteristics of Indian languages and their scripts to propose an approach based on common multilingual Latin-based encodings (WX notation) that take advantage of language similarity while addressing the morphological complexity issue in NMT. These multilingual Latin-based encodings in NMT, together with Byte Pair Embedding (BPE) allow us to better exploit their phonetic and orthographic as well as lexical similarities to improve the translation quality by projecting different but similar languages on the same orthographic-phonetic character space. We verify the proposed approach by demonstrating experiments on similar language pairs (Gujarati↔Hindi, Marathi↔Hindi, Nepali↔Hindi, Maithili↔Hindi, Punjabi↔Hindi, and Urdu↔Hindi) under low resource conditions. The proposed approach shows an improvement in a majority of cases, in one case as much as ∼10 BLEU points compared to baseline techniques for similar language pairs. We also get up to ∼1 BLEU points improvement on distant and zero-shot language pairs.

show abstract