Hybrid machine translation for English to Marathi: A research evaluation in Machine Translation: (Hybrid translator)

Salunkhe, Pramod; Kadam, Aniket; Joshi, Sarang; Patil, S.H.; Thakore, Devendrasingh; Jadhav, Shrikant

doi:10.1109/iceeot.2016.7754822

Cited by 23 publications

(6 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tamil to English Cross Lingual Information Retrieval System for Agricultural Domain Using SVM’ uses one such approach of machine translation where a bilingual dictionary for translating the user queries and n‐gram‐based approach are used to recover the problem of Word Sense Disambiguation (Saravanan & Sathish, 2016). Other language translations from English to Marathi (Salunkhe et al, 2016), English to Hindi (Malik & Baghel, 2016), and English to Arabic (Shaalan et al, 2010) have been carried out for the agricultural domain as well. Marian (Junczys‐Dowmunt et al, 2018) is a self‐contained Neural Machine translation framework developed on C++ to perform machine translation.…”

Section: Related Workmentioning

confidence: 99%

PooRaa‐Agri KG: An agricultural knowledge graph‐based simplified multilingual query system

Sivakumar,

Srinivasan,

Kannan

et al. 2023

Expert Systems

View full text Add to dashboard Cite

The current work proposes PooRaa‐Agri KG, an agricultural knowledge graph‐based simplified multilingual query system that works in real time to provide concise answers for agriculture‐based queries. The proposed approach accommodates real‐time and low‐resource queries in English and Hindi with a novel multi‐stage solution consisting of data pre‐processing, sentence simplification, triplet extraction, knowledge graph generation, sentence reconstruction, query‐to‐reconstructed sentence matching, and machine translation as its sub‐modules. In this work, a novel combination of rule‐based sentence simplification and triplet extraction is carried out resulting in a triplet similarity score of 86.56% for the extracted triplets. This method is superior to the existing triplet extraction method whose triplet similarity score was found to be 60.65%. Further, the proposed work makes use of heuristic rules to reconstruct sentences which when evaluated by human evaluators for meaningfulness and grammar resulted in a score of 3.09/4 and 2.95/4 respectively. To complete end‐to‐end communication in the proposed system, a similarity‐based query answer system is proposed in this work.

show abstract

Section: Related Workmentioning

confidence: 99%

PooRaa‐Agri KG: An agricultural knowledge graph‐based simplified multilingual query system

Sivakumar,

Srinivasan,

Kannan

et al. 2023

Expert Systems

View full text Add to dashboard Cite

show abstract

“…The excerpt-based approach enjoys advantage with formality, cohesion and contextual relevance. Active learning methods, on the contrary, do not have consecutive sentences and therefore lose local coherence and pose challenges to human translators (Muntés Mulero et al, 2012;Denkowski, 2015;Sperber et al, 2017;Maruf et al, 2019;Webster et al, 2020;Zhou and Waibel, 2021a;Salunkhe et al, 2016). This is an active research area.…”

Section: Future Workmentioning

confidence: 99%

Train Global, Tailor Local: Minimalist Multilingual Translation into Endangered Languages

Zhou,

Niehues,

Waibel

2023

Proceedings of the the Sixth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2023)

View full text Add to dashboard Cite

In many humanitarian scenarios, translation into severely low resource languages often does not require a universal translation engine, but a dedicated text-specific translation engine. For example, healthcare records, hygienic procedures, government communication, emergency procedures and religious texts are all limited texts. While generic translation engines for all languages do not exist, translation of multilingually known limited texts into new, endangered languages may be possible and reduce human translation effort. We attempt to leverage translation resources from many rich resource languages to efficiently produce best possible translation quality for a well known text, which is available in multiple languages, in a new, severely low resource language. We examine two approaches: 1.) best selection of seed sentences to jump start translations in a new language in view of best generalization to the remainder of a larger targeted text(s), and 2.) we adapt large general multilingual translation engines from many other languages to focus on a specific text in a new, unknown language. We find that adapting large pretrained multilingual models to the domain/text first and then to the severely low resource language works best. If we also select a best set of seed sentences, we can improve average chrF performance on new test languages from a baseline of 21.9 to 50.7, while reducing the number of seed sentences to only ∼1,000 in the new, unknown language.

show abstract

“…In the last few decades, a number of works have been done on Machine Translation (MT), the initial attempt was made in the 1950s (Booth, 1955). A number of approaches have been tried out by researchers, for example, rule-based MT (Poornima et al, 2011), hybrid-based MT (Salunkhe et al, 2016), and data-driven MT (Wong et al, 2006). All of these approaches have their own advantages and disadvantages.…”

Section: Related Workmentioning

confidence: 99%

NLPRL at WAT2019: Transformer-based Tamil – English Indic Task Neural Machine Translation System

Kumar¹,

Singh²

2019

Proceedings of the 6th Workshop on Asian Translation

View full text Add to dashboard Cite

This paper describes the Machine Translation (MT) system submitted by the NLPRL team for the Tamil -English Indic Task at WAT 2019. We presented the Neural Machine Translation (NMT) system based on the Transformer approach. Training and performance of the model are evaluated on the En-Tam corpus (An English-Tamil Parallel Corpus) collected by researchers at UFAL (Institute of Formal and Applied Linguistics). The evaluation of the model done using Adequacy, BLEU, RIBES, and AM-FM scores, and the model improves translation in terms of Adequacy, RIBES and AM-FM as compared to the baseline.

show abstract

Hybrid machine translation for English to Marathi: A research evaluation in Machine Translation: (Hybrid translator)

Cited by 23 publications

References 1 publication

PooRaa‐Agri KG: An agricultural knowledge graph‐based simplified multilingual query system

PooRaa‐Agri KG: An agricultural knowledge graph‐based simplified multilingual query system

Train Global, Tailor Local: Minimalist Multilingual Translation into Endangered Languages

NLPRL at WAT2019: Transformer-based Tamil – English Indic Task Neural Machine Translation System

Contact Info

Product

Resources

About