A review of machine transliteration, translation, evaluation metrics and datasets in Indian Languages

Jha, Abhinav; Patil, Hemprasad Yashwant

doi:10.1007/s11042-022-14273-1

Cited by 5 publications

(6 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both of these works use a cascade approach. As highlighted earlier, building a pipeline for English to Punjabi speech translation using the cascade approach is limited by the unavailability of state-of-the-art ASR [30], [9], MT [31], and S2T models for Punjabi. Specifically, there is no S2T model available for Punjabi [29].…”

Section: Direct Speech-to-speech Translation (S2st) Modelsmentioning

confidence: 99%

Untitled

2024

IJCI

View full text Add to dashboard Cite

Speech-to-speech translation is yet to reach the same level of coverage as text-to-text translation systems. The current speech technology is highly limited in its coverage of over 7000 languages spoken worldwide, leaving more than half of the population deprived of such technology and shared experiences. With voice-assisted technology (such as social robots and speech-to-text apps) and auditory content (such as podcasts and lectures) on the rise, ensuring that the technology is available for all is more important than ever. Speech translation can play a vital role in mitigating technological disparity and creating a more inclusive society. With a motive to contribute towards speech translation research for low-resource languages, our work presents a direct speech-to-speech translation model for one of the Indic languages called Punjabi to English. Additionally, we explore the performance of using a discrete representation of speech called discrete acoustic units as input to the Transformer-based translation model. The model, abbreviated as Unit-to-Unit Translation (U2UT), takes a sequence of discrete units of the source language (the language being translated from) and outputs a sequence of discrete units of the target language (the language being translated to). Our results show that the U2UT model performs better than the Speechto-Unit Translation (S2UT) model by a 3.69 BLEU score.

show abstract

Section: Direct Speech-to-speech Translation (S2st) Modelsmentioning

confidence: 99%

Untitled

2024

IJCI

View full text Add to dashboard Cite

show abstract

“…Input: In NER approaches, there are mainly two types of problem faced for input i.e., code mixing and transliteration. To create NER dataset for Indian Languages that covers different entities like name of person, place, organization and date etc., which is time consuming or labor-intensive process [114]. The challenges of input process are discussed below:…”

Section: Issues and Challengesmentioning

confidence: 99%

State-of-art approach for Indian Language based on NER: Comprehensive Review

Pandey,

Nathani

2024

Preprint

View full text Add to dashboard Cite

Named Entity Recognition (NER) is a fundamental task of natural language processing (NLP) that focuses on the identification and classification of named entities such as name of individual persons, location, organization and dates within the text. NER plays a pivotal role in various NLP applications, including information extraction, question answering, text summarization and sentiment analysis. Natural language processing's (NLPs) fundamental issue is named entity recognition (NER). While extensive research has been conducted on NER for English and Hindi, the complexities of Indian languages present unique challenges that require customized solutions. Working with NER for Indian languages is a difficult endeavor with limited resources available. This article provides a comprehensive review of NER approaches tailored for Indian languages. Indian languages pose unique challenges to NER due to their rich morphological and syntactic variations, script diversity and limited annotated data availability. This paper reviews the various techniques and methodologies employed in NER for Indian languages, including rule-based, machine learning and deep learning approaches. It analyzes the strengths and limitations of each approach. Additionally, this article examines the recent advancements in transfer learning and multilingual models, showcasing their potential in improving NER performance across Indian languages. This paper aims to guide researchers and practitioners in the development of NER systems for Indian languages and foster further advancements in this field. This article also provides a comprehensive review of the diverse approaches employed for NER in Indian languages, highlighting the strength and limitations as well.

show abstract

“…One of the key drivers behind this progress is the development and adoption of neural machine translation (NMT) models, which have significantly improved the quality and fluency of translations by leveraging deep learning techniques [11]. These models are adept at capturing complex grammatical structures, idiomatic expressions, and linguistic nuances, thereby producing translations that closely mimic natural language usage [12]. Additionally, transformer-based architectures, such as BERT (Bidirectional Encoder Representations from Transformers) and GPT (Generative Pre-trained Transformer), have further advanced cross-language translation capabilities.…”

Section: Introductionmentioning

confidence: 99%

Cross-Language Translation and Comparative Study of English Literature Using Machine Translation Algorithms

Shanshan Wang

2024

jes

View full text Add to dashboard Cite

Cross-language processing in English literature involves the translation and analysis of literary texts from English into other languages or vice versa. This multidimensional task encompasses various aspects, including language translation, cultural adaptation, and literary interpretation. Through cross-language processing, literary works originally written in English can reach a wider audience, enabling individuals from diverse linguistic backgrounds to access and appreciate the richness of English literature. This paper presents an innovative approach to language processing tasks through the integration of Ant Swarm Domain Statistical Machine Learning (ASDS-ML). Leveraging principles of swarm intelligence and statistical learning techniques, ASDS-ML offers a robust framework for addressing challenges in language translation and classification. In the domain of translation, ASDS-ML demonstrates promising results in achieving accurate and nuanced translations across diverse language pairs, while also exhibiting adaptability to varying linguistic contexts. Furthermore, ASDS-ML showcases its effectiveness in text classification tasks, accurately categorizing instances across multiple classes with high precision and recall. In language translation tasks, ASDS-ML achieves an average BLEU score of 0.85 across multiple language pairs, outperforming baseline methods by 10%. Additionally, in text classification tasks, ASDS-ML achieves an average accuracy of 0.92 across ten different classes, surpassing existing approaches by 5%.

show abstract

A review of machine transliteration, translation, evaluation metrics and datasets in Indian Languages

Cited by 5 publications

References 61 publications

Untitled

Untitled

State-of-art approach for Indian Language based on NER: Comprehensive Review

Cross-Language Translation and Comparative Study of English Literature Using Machine Translation Algorithms

Contact Info

Product

Resources

About